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

    Neuronpedia

    INDEX
    Explanations

    without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ruba
    -0.07
    obs
    -0.07
    viol
    -0.06
     Rub
    -0.06
     Нет
    -0.06
     XF
    -0.06
    Rub
    -0.06
    ジョ
    -0.06
     InvalidArgumentException
    -0.06
     δια
    -0.06
    POSITIVE LOGITS
    (od
    0.06
    Distance
    0.06
     shipping
    0.06
     muscular
    0.06
     oder
    0.06
     TableView
    0.06
     Distance
    0.06
    jected
    0.06
     GUIStyle
    0.06
     );↵
    0.06
    Act Density 0.003%

    No Known Activations