Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    sections of text that lack any notable activations, indicating it is likely looking for specific structured data or entities that are not present

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows stop words or punctuation

    np_acts-logits-general · gemini-2.0-flash

    is/be followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.78
     autorytatywna
    -0.78
     betweenstory
    -0.73
     lenker
    -0.71
     تضيفلها
    -0.60
     חיצוניים
    -0.60
    chord
    -0.60
     themſelves
    -0.59
     yyl
    -0.58
     auroit
    -0.58
    POSITIVE LOGITS
     the
    0.66
    requireNonNull
    0.54
     truly
    0.54
     where
    0.53
     an
    0.52
    DebuggerNonUser
    0.51
    ModelSerializer
    0.51
     lī
    0.49
     a
    0.49
    setContentView
    0.48
    Act Density 0.142%

    No Known Activations