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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical definitions and notations

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

    referencing definitions or theorems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GOTREF
    -0.47
     maxX
    -0.44
     papaya
    -0.41
     affitto
    -0.41
    TargetException
    -0.40
     plumes
    -0.40
    lobo
    -0.40
    EndContext
    -0.39
    gnat
    -0.39
    ulls
    -0.39
    POSITIVE LOGITS
    similar
    0.56
    same
    0.54
     دیکھیے
    0.54
     similar
    0.53
    Similar
    0.50
     mêmes
    0.49
    contentLoaded
    0.49
    QMetaType
    0.49
     dieselben
    0.49
    Same
    0.49
    Act Density 0.180%

    No Known Activations