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

    Neuronpedia

    INDEX
    Explanations

    Formal communications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    커스
    -0.07
     jet
    -0.07
    (___
    -0.07
     ارائه
    -0.07
    ΜΑ
    -0.07
    lauf
    -0.06
    циях
    -0.06
    фек
    -0.06
    according
    -0.06
     lofty
    -0.06
    POSITIVE LOGITS
    (remove
    0.07
    .isRequired
    0.06
    —that
    0.06
     свойства
    0.06
    .recycle
    0.06
     deduct
    0.06
     Barrel
    0.06
    струмент
    0.06
     sparkling
    0.06
     joining
    0.06
    Act Density 0.034%

    No Known Activations