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

    Neuronpedia

    INDEX
    Explanations

    science articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Az
    -0.07
     Az
    -0.07
     руку
    -0.06
    _ll
    -0.06
    Africa
    -0.06
     magnet
    -0.06
    Z
    -0.06
    ,ch
    -0.06
    _stub
    -0.06
    R
    -0.06
    POSITIVE LOGITS
    enuous
    0.07
     thiện
    0.07
     그가
    0.06
     Комп
    0.06
    َ
    0.06
    мо
    0.06
     HMAC
    0.06
    跨
    0.06
     meticulously
    0.06
    ertos
    0.06
    Act Density 0.001%

    No Known Activations