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

    Neuronpedia

    INDEX
    Explanations

    copyright reserved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Quin
    -0.78
     lo
    -0.73
    QList
    -0.71
    gan
    -0.70
     inac
    -0.66
    derry
    -0.66
    list
    -0.66
    estyles
    -0.65
     major
    -0.65
     все
    -0.63
    POSITIVE LOGITS
    Видео
    0.73
     Iber
    0.73
    Składniki
    0.72
     giro
    0.69
    Może
    0.68
    Proč
    0.68
    Då
    0.67
     לאחר
    0.66
    Tipps
    0.66
    Děkuji
    0.66
    Act Density 0.070%

    No Known Activations