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

    Neuronpedia

    INDEX
    Explanations

    numerical values and mathematical operators

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

    zero sequences and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.63
     виправивши
    -0.61
    __(/*!
    -0.58
    Tikang
    -0.56
     informée
    -0.54
     surla
    -0.53
     sumpay
    -0.53
    RegistryLite
    -0.53
    ReusableCell
    -0.52
    IonicModule
    -0.51
    POSITIVE LOGITS
    silent
    0.40
    skip
    0.39
    to
    0.39
    empty
    0.39
     uLocal
    0.38
    hook
    0.38
    quite
    0.38
    uffff
    0.38
     quite
    0.37
    hint
    0.37
    Act Density 0.171%

    No Known Activations