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

    Neuronpedia

    INDEX
    Explanations

    Identification, New York

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     infatti
    -0.89
    了你
    -0.84
     모든
    -0.81
    悶
    -0.81
    ără
    -0.79
     bayer
    -0.78
    meniz
    -0.78
     toolStrip
    -0.76
     ajustar
    -0.75
    鱈
    -0.75
    POSITIVE LOGITS
     (_,
    0.84
    大量
    0.82
    További
    0.80
    lot
    0.80
    laining
    0.77
    捷
    0.77
     nisi
    0.77
     bitterly
    0.75
    ｅ
    0.75
    ge
    0.73
    Act Density 0.000%

    No Known Activations