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

    Neuronpedia

    INDEX
    Explanations

    Population

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (N
    -0.07
    گار
    -0.07
    Sprite
    -0.06
     floated
    -0.06
    rible
    -0.06
    ление
    -0.06
     soften
    -0.06
     Triangle
    -0.06
    жение
    -0.06
    ينة
    -0.06
    POSITIVE LOGITS
     продовж
    0.06
    接受
    0.06
     ShoppingCart
    0.06
     elo
    0.06
     мог
    0.06
    clock
    0.06
     Flesh
    0.06
     sag
    0.06
     آش
    0.06
     아�
    0.06
    Act Density 0.002%

    No Known Activations