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

    Neuronpedia

    INDEX
    Explanations

    Sul

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    StackTrace
    -0.07
    :numel
    -0.06
    (Entity
    -0.06
    <TEntity
    -0.06
    .Alert
    -0.06
     eminent
    -0.06
    /article
    -0.06
    литель
    -0.06
    Sprite
    -0.05
    	Error
    -0.05
    POSITIVE LOGITS
    íž
    0.08
    PTION
    0.07
    bsites
    0.07
    زم
    0.07
    их
    0.07
     öz
    0.06
    achable
    0.06
    सर
    0.06
    Bay
    0.06
    μί
    0.06
    Act Density 0.002%

    No Known Activations