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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    胩
    -0.07
     respectfully
    -0.07
     thì
    -0.07
    subtype
    -0.06
    各个
    -0.06
     gibt
    -0.06
    .vol
    -0.06
     구
    -0.06
     various
    -0.06
    .focus
    -0.06
    POSITIVE LOGITS
     демо
    0.07
    เทคน
    0.07
    威慑
    0.07
    refixer
    0.07
    {}↵
    0.07
    リフォーム
    0.07
     Lik
    0.06
     Torres
    0.06
    قات
    0.06
    ❈
    0.06
    Act Density 0.001%

    No Known Activations