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

    Neuronpedia

    INDEX
    Explanations

    .org

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vander
    -0.07
    <strong
    -0.07
     Bip
    -0.07
     Ав
    -0.07
     liberty
    -0.06
     Ey
    -0.06
     Craw
    -0.06
    uegos
    -0.06
    derived
    -0.06
    initial
    -0.06
    POSITIVE LOGITS
    '].'/
    0.07
    ิศ
    0.07
    .IS
    0.07
    럽
    0.06
     بود
    0.06
    ulators
    0.06
     pwd
    0.06
     هزار
    0.06
    ‌رس
    0.06
    verte
    0.06
    Act Density 0.003%

    No Known Activations