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
     �
    -0.07
     Мик
    -0.06
    WHERE
    -0.06
    .df
    -0.06
    няття
    -0.06
     Kathy
    -0.06
     уровня
    -0.06
     karş
    -0.06
     giov
    -0.06
     apare
    -0.06
    POSITIVE LOGITS
    "bytes
    0.07
    .slice
    0.07
    ิโล
    0.07
     CLOSED
    0.06
     armour
    0.06
     deluxe
    0.06
    Interface
    0.06
    LOS
    0.06
    Anchor
    0.06
     مرکزی
    0.06
    Act Density 0.000%

    No Known Activations