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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fon
    -0.07
     enfants
    -0.07
    بار
    -0.07
    تد
    -0.07
    _location
    -0.07
    不到位
    -0.07
    槛
    -0.07
     mornings
    -0.06
     numberOf
    -0.06
    beginTransaction
    -0.06
    POSITIVE LOGITS
     partes
    0.07
    一部
    0.07
    (eval
    0.07
     Decorating
    0.07
     ",",
    0.06
     proves
    0.06
    移民
    0.06
    Study
    0.06
    --
    0.06
     became
    0.06
    Act Density 0.003%

    No Known Activations