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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    factor
    -0.06
    Sharper
    -0.06
     //////////////////////////////////////////////////////////////////////////
    -0.06
    UiThread
    -0.06
     자기
    -0.06
    _Invoke
    -0.06
    /******************************************************************************/↵
    -0.06
    
    -0.06
     )(
    -0.06
    GROUP
    -0.06
    POSITIVE LOGITS
     Lucy
    0.07
     exciting
    0.07
     Angry
    0.07
     또는
    0.07
     انت
    0.07
     communicated
    0.06
     dateString
    0.06
     mutate
    0.06
     От
    0.06
    odont
    0.06
    Act Density 0.012%

    No Known Activations