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
     prob
    -0.06
     USB
    -0.06
     Register
    -0.06
    .angle
    -0.06
     aud
    -0.06
    ip
    -0.06
    cessive
    -0.06
     Horm
    -0.06
     �
    -0.06
    елич
    -0.06
    POSITIVE LOGITS
     음
    0.07
     minion
    0.06
    员
    0.06
     putas
    0.06
    立て
    0.06
    나무
    0.06
    _pago
    0.06
     απο
    0.06
    _topic
    0.06
    ('.');↵
    0.06
    Act Density 0.381%

    No Known Activations