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

    Neuronpedia

    INDEX
    Explanations

    looking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uria
    -0.06
    살
    -0.06
     commenting
    -0.06
     llevar
    -0.06
    İSİ
    -0.06
     otevř
    -0.06
     suicidal
    -0.06
    .filter
    -0.06
    Ru
    -0.06
    lashes
    -0.06
    POSITIVE LOGITS
     Prem
    0.07
    のだ
    0.06
     Turnbull
    0.06
     �
    0.06
     Απ
    0.06
    (gray
    0.06
    kits
    0.06
     dit
    0.06
     druhé
    0.06
     Peb
    0.06
    Act Density 0.019%

    No Known Activations