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

    Neuronpedia

    INDEX
    Explanations

    multiple

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fitzgerald
    -0.09
    _FORWARD
    -0.08
    -motion
    -0.07
     coração
    -0.07
    뜻
    -0.07
    碗
    -0.07
     cabeza
    -0.07
    iology
    -0.07
    living
    -0.07
     CHE
    -0.07
    POSITIVE LOGITS
     weap
    0.08
     compat
    0.07
    uding
    0.07
    .rand
    0.07
    iants
    0.06
    мес
    0.06
    新形势下
    0.06
    ige
    0.06
    콴
    0.06
    (rand
    0.06
    Act Density 0.025%

    No Known Activations