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

    Neuronpedia

    INDEX
    Explanations

    being

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     See
    -0.06
    "If
    -0.06
    .Once
    -0.06
     hôm
    -0.06
     historic
    -0.06
    sector
    -0.06
     Formula
    -0.06
     Sales
    -0.06
     SIDE
    -0.06
    (children
    -0.06
    POSITIVE LOGITS
    럴
    0.07
     жиз
    0.07
     kp
    0.07
    nah
    0.07
    ानव
    0.06
     kInstruction
    0.06
    馆
    0.06
    atu
    0.06
    _arch
    0.06
    怀
    0.06
    Act Density 0.059%

    No Known Activations