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

    Neuronpedia

    INDEX
    Explanations

    float

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    estyle
    -0.07
    -formed
    -0.07
    .der
    -0.07
     рамках
    -0.07
    цов
    -0.06
     돌아
    -0.06
    ानसभ
    -0.06
    상을
    -0.06
    -resolution
    -0.06
    ezpeč
    -0.06
    POSITIVE LOGITS
    >>>>
    0.07
     Manhattan
    0.06
    0.06
     Counter
    0.06
    gmail
    0.06
     Chic
    0.06
    0.06
    领导
    0.05
     Maar
    0.05
    HEY
    0.05
    Act Density 0.000%

    No Known Activations