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

    Neuronpedia

    INDEX
    Explanations

    negative situations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.93
    WireFormatLite
    -0.91
     متعلقه
    -0.87
    出版年
    -0.78
     Biôgrafia
    -0.75
    ergies
    -0.71
    IsMutable
    -0.71
     autorytatywna
    -0.69
     distanciation
    -0.69
     समीक्षक
    -0.67
    POSITIVE LOGITS
     or
    0.73
     negative
    0.59
     but
    0.57
     caused
    0.57
     causing
    0.56
     worse
    0.55
     yet
    0.54
     dangerous
    0.49
    ,'
    0.49
     --
    0.48
    Act Density 0.033%

    No Known Activations