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

    Neuronpedia

    INDEX
    Explanations

    programming language syntax related to handling unknown fields and data serialization

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

    SwiftProtobuf code or function calls

    np_acts-logits-general · gemini-2.0-flash

    traverse visitor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    に使用
    -0.53
     permesso
    -0.50
     value
    -0.48
     creen
    -0.47
     ddelweddau
    -0.47
     bulunur
    -0.47
     esternos
    -0.47
    pausal
    -0.47
    četně
    -0.46
    割
    -0.46
    POSITIVE LOGITS
    DockStyle
    0.81
    AccessorTable
    0.78
    AnimationsModule
    0.74
     ModelExpression
    0.73
    matchCondition
    0.71
     useStyles
    0.71
    ResumeLayout
    0.70
     BrowserModule
    0.68
    WriteBarrier
    0.67
    UIControlState
    0.67
    Act Density 0.116%

    No Known Activations