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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a lack of effect or difference.

    oai_token-act-pair · gemini-2.0-flash

    difference

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.70
    ″]
    -0.65
     autorytatywna
    -0.65
     مرئيه
    -0.62
     незавершена
    -0.57
     Ditto
    -0.57
    setVerticalGroup
    -0.57
    ఔ
    -0.57
    RenderAtEndOf
    -0.57
    PerformLayout
    -0.56
    POSITIVE LOGITS
     difference
    0.69
    difference
    0.57
     care
    0.57
    әр
    0.57
    差
    0.52
    care
    0.52
     importância
    0.51
     problem
    0.51
     Difference
    0.51
     tụ
    0.50
    Act Density 1.561%

    No Known Activations