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

    Neuronpedia

    INDEX
    Explanations

    facts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    체
    -0.07
     Zap
    -0.07
    (match
    -0.06
     regularly
    -0.06
    '].'"
    -0.06
    γού
    -0.06
     marches
    -0.06
    _delay
    -0.06
     reportedly
    -0.06
    ieurs
    -0.06
    POSITIVE LOGITS
    Logic
    0.08
     Lancaster
    0.07
    Pacific
    0.06
    .Quantity
    0.06
    Sad
    0.06
     PyErr
    0.06
    лл
    0.06
    ична
    0.06
     Conexion
    0.06
    κας
    0.06
    Act Density 0.003%

    No Known Activations