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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notations related to advanced concepts

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

    official reserves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.52
    WithIOException
    -0.45
    というもの
    -0.40
     anzu
    -0.38
    龇
    -0.38
    WireFormatLite
    -0.36
    uttgart
    -0.36
     Ang
    -0.35
    pon
    -0.34
     StringField
    -0.34
    POSITIVE LOGITS
    ьаж
    0.58
    SuspendLayout
    0.48
    astify
    0.47
     tabPage
    0.47
    TagMode
    0.46
    conio
    0.46
    ymce
    0.45
    OGND
    0.44
    nezeu
    0.44
     solas
    0.43
    Act Density 0.027%

    No Known Activations