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

    Neuronpedia

    INDEX
    Explanations

    y (area between curves)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     waardoor
    -0.08
     salah
    -0.08
     తర
    -0.08
     Ä
    -0.08
     Tears
    -0.07
    iczne
    -0.07
    Filed
    -0.07
    Declar
    -0.07
     viên
    -0.07
    Titel
    -0.07
    POSITIVE LOGITS
     máxim
    0.08
     maxima
    0.07
     dů
    0.07
     соответств
    0.07
     올라
    0.07
     occupy
    0.07
     positi
    0.07
     �
    0.07
     Occup
    0.07
     pozy
    0.07
    Act Density 0.023%

    No Known Activations