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

    Neuronpedia

    INDEX
    Explanations

    actors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    categorias
    -0.07
     jeune
    -0.06
    Vin
    -0.06
     أحمد
    -0.06
    нит
    -0.06
     sto
    -0.06
    etherlands
    -0.06
     energie
    -0.06
    玄
    -0.06
     Caught
    -0.06
    POSITIVE LOGITS
    ammo
    0.06
     пап
    0.06
    _Params
    0.06
     Vi
    0.06
     goog
    0.06
    /payment
    0.06
    (Yii
    0.06
    Cnt
    0.06
     noticeable
    0.06
    ΟΔ
    0.06
    Act Density 0.013%

    No Known Activations