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

    Neuronpedia

    INDEX
    Explanations

    comments and annotations in code or markup text

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

    added text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.49
    ⓧ
    -0.48
    centralwidget
    -0.47
     SqlCommand
    -0.46
     ExecuteAsync
    -0.45
    AutoScaleMode
    -0.43
    bootstrapcdn
    -0.43
     MainAxisSize
    -0.42
    principalColumn
    -0.42
     الحره
    -0.42
    POSITIVE LOGITS
     additional
    0.69
     added
    0.64
    added
    0.62
     추가
    0.62
     Added
    0.60
     adicionales
    0.60
     tambahan
    0.59
    Additional
    0.59
    additional
    0.59
     Additional
    0.57
    Act Density 0.032%

    No Known Activations