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

    Neuronpedia

    INDEX
    Explanations

    para

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wig
    -0.07
    on
    -0.07
     Gol
    -0.07
    629
    -0.06
     lookout
    -0.06
    ountry
    -0.06
     unserer
    -0.06
     von
    -0.06
     phần
    -0.06
     Spor
    -0.06
    POSITIVE LOGITS
    _CANCEL
    0.07
     کارخانه
    0.07
     enterprises
    0.07
    оку
    0.07
     corresponding
    0.07
    Sometimes
    0.07
    _factory
    0.06
    　　 　
    0.06
    IFO
    0.06
    _Event
    0.06
    Act Density 0.059%

    No Known Activations