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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ومان
    -0.07
    кор
    -0.07
     Coleman
    -0.06
    setter
    -0.06
     Sur
    -0.06
    imony
    -0.06
    Imp
    -0.06
    $L
    -0.06
     드
    -0.06
     XL
    -0.06
    POSITIVE LOGITS
    (loss
    0.07
     elé
    0.06
     attorneys
    0.06
    _include
    0.06
     Athe
    0.06
    yte
    0.06
    那个
    0.06
    Ptr
    0.06
     erase
    0.06
     ranking
    0.06
    Act Density 0.004%

    No Known Activations