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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and notation

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

    mathematical expressions and inequalities

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

    mathematical or code symbols and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     “
    -0.58
     (“
    -0.55
    <eos>
    -0.50
    ，“
    -0.48
     /(
    -0.48
     ),
    -0.47
     )
    -0.45
    ompi
    -0.43
     ("
    -0.43
     Certainly
    -0.43
    POSITIVE LOGITS
    awtextra
    0.81
     незавершена
    0.80
    InstrumentedTest
    0.80
     doInBackground
    0.79
    Jeografia
    0.77
    IUrlHelper
    0.73
     AppColors
    0.73
     requestCode
    0.72
    TypedDataSet
    0.70
    "
    0.67
    Act Density 0.030%

    No Known Activations