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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kiểm
    -0.07
     cambio
    -0.07
     örnek
    -0.07
     Severity
    -0.06
     开
    -0.06
     Под
    -0.06
     as
    -0.06
     sł
    -0.06
    しか
    -0.06
    .Cancel
    -0.06
    POSITIVE LOGITS
    ститут
    0.07
    checkpoint
    0.07
    uters
    0.06
     звіль
    0.06
    krát
    0.06
     хорошо
    0.06
     --↵↵
    0.06
    公路
    0.06
    iforn
    0.06
    _ELEMENTS
    0.06
    Act Density 0.000%

    No Known Activations