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

    Neuronpedia

    INDEX
    Explanations

    programming symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Voice
    -0.07
    -0.07
    """↵
    -0.06
    -0.06
    ائق
    -0.06
    pons
    -0.06
     REC
    -0.06
     Fuji
    -0.06
    اوند
    -0.06
    \xb
    -0.06
    POSITIVE LOGITS
     možnosti
    0.07
    이에
    0.06
     ningún
    0.06
    üsseldorf
    0.06
    ادت
    0.06
    osto
    0.06
    .omg
    0.06
    _ml
    0.06
     ErrorHandler
    0.06
    Fecha
    0.06
    Act Density 0.078%

    No Known Activations