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

    Neuronpedia

    INDEX
    Explanations

    threw

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hom
    -0.07
     八
    -0.06
    Ub
    -0.06
    metrics
    -0.06
    grown
    -0.06
    *(-
    -0.06
    	column
    -0.06
    "B
    -0.06
    ISED
    -0.06
    Ошибка
    -0.06
    POSITIVE LOGITS
     FITNESS
    0.08
    etics
    0.07
    rec
    0.07
    angled
    0.07
     имя
    0.07
    JECT
    0.06
     کردند
    0.06
     ссыл
    0.06
    !↵↵
    0.06
    0.06
    Act Density 0.013%

    No Known Activations