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

    Neuronpedia

    INDEX
    Explanations

    programming libraries and modules

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

    python module imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.63
    SourceChecksum
    -0.57
    RegressionTest
    -0.55
     Италијани
    -0.55
     Daß
    -0.53
     AssemblyTitle
    -0.52
    رشف
    -0.51
    wnież
    -0.51
    parsedMessage
    -0.50
    principalColumn
    -0.49
    POSITIVE LOGITS
    <0xD8>
    0.46
     Blind
    0.40
    AxisAlignment
    0.40
    getActiveSheet
    0.39
     Green
    0.39
    ToBounds
    0.39
     воро
    0.39
     
    0.39
    ：“……”
    0.38
     serde
    0.37
    Act Density 0.001%

    No Known Activations