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

    Neuronpedia

    INDEX
    Explanations

    T

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Expl
    -0.07
    hydrate
    -0.07
     управ
    -0.06
    _mi
    -0.06
    blick
    -0.06
     GANG
    -0.06
     accompanying
    -0.06
    _In
    -0.06
     Mickey
    -0.06
     смерть
    -0.06
    POSITIVE LOGITS
    ,w
    0.08
     W
    0.07
    PasswordField
    0.07
    OutOfRange
    0.07
    품
    0.06
     فرم
    0.06
    .getD
    0.06
     krás
    0.06
    .flash
    0.06
    .Host
    0.06
    Act Density 0.037%

    No Known Activations