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

    Neuronpedia

    INDEX
    Explanations

    instances of classes related to data unmarshalling in programming contexts

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

    programming language constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.67
     kasarigan
    -0.63
     surla
    -0.63
     InputDecoration
    -0.62
    出版年
    -0.55
    xnn
    -0.48
    -------
    -0.46
    jspb
    -0.46
    eqn
    -0.46
    iedenen
    -0.46
    POSITIVE LOGITS
    لينكات
    1.16
     مرئيه
    1.07
    GetKeyDown
    1.00
    tableLayoutPanel
    0.78
    ValueGenerated
    0.70
     مخطط
    0.65
    GetKey
    0.59
    GrantedAuthority
    0.58
    ApiModel
    0.57
     randint
    0.57
    Act Density 0.001%

    No Known Activations