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

    Neuronpedia

    INDEX
    Explanations

    state declarations and method signatures in class definitions

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

    Code snippets or programming terms

    np_acts-logits-general · gemini-2.0-flash

    constructor arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.57
    таратура
    -0.54
    baye
    -0.54
    Chham
    -0.53
     defy
    -0.52
    Források
    -0.51
    InjectAttribute
    -0.50
     חיצוניים
    -0.49
    AutoScaleMode
    -0.49
    SourceChecksum
    -0.48
    POSITIVE LOGITS
    colgroup
    0.64
     becauſe
    0.60
     précédents
    0.60
    ؤلاء
    0.60
     évaluations
    0.59
     myſelf
    0.59
    ptonshire
    0.59
     theſe
    0.58
    setViewportView
    0.57
    Населення
    0.55
    Act Density 0.023%

    No Known Activations