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

    Neuronpedia

    INDEX
    Explanations

    performance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <|reserved_200016|>
    -0.09
     screened
    -0.08
    Govern
    -0.08
     downloading
    -0.08
    <|endoftext|>
    -0.07
     governance
    -0.07
    Downloading
    -0.07
    Fax
    -0.07
     sanar
    -0.07
    lom
    -0.07
    POSITIVE LOGITS
     Вес
    0.10
    _rating
    0.10
     bonus
    0.09
     第二
    0.09
    评级
    0.09
     प्रतिशत
    0.09
     bônus
    0.09
     beoord
    0.09
     정도
    0.09
     बोनस
    0.09
    Act Density 0.002%

    No Known Activations