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

    Neuronpedia

    INDEX
    Explanations

    structural elements of code, particularly related to class definitions and method implementations

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

    Java annotations and public declarations

    np_acts-logits-general · gemini-2.0-flash

    public method annotations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.54
     createState
    -0.52
    CPtr
    -0.50
    unknownFields
    -0.48
    istory
    -0.46
     <",
    -0.45
    はじめに
    -0.45
    cioc
    -0.45
     TAMBÉM
    -0.44
     autorytatywna
    -0.43
    POSITIVE LOGITS
    énéral
    0.63
    coltura
    0.56
    ⓧ
    0.55
     Survivors
    0.54
    public
    0.54
    ButtonItem
    0.53
    ScopeManager
    0.53
    middels
    0.53
     snippetHide
    0.53
     fullt
    0.52
    Act Density 0.048%

    No Known Activations