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

    Neuronpedia

    INDEX
    Explanations

    VALUES

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    //--------------------------------
    -0.07
    _Att
    -0.07
     yapılması
    -0.07
    _edit
    -0.07
    _attached
    -0.07
    _YUV
    -0.06
     hài
    -0.06
    .Name
    -0.06
     программ
    -0.06
    ارش
    -0.06
    POSITIVE LOGITS
    electronics
    0.06
    ncias
    0.06
     york
    0.06
    οντας
    0.06
    iances
    0.06
    bucks
    0.06
     قب
    0.06
    warts
    0.06
    eways
    0.06
     Directors
    0.06
    Act Density 0.001%

    No Known Activations