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

    Neuronpedia

    INDEX
    Explanations

    nuclear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     등
    -0.07
     firefighter
    -0.07
     Gaussian
    -0.07
    说话
    -0.07
     poil
    -0.06
    ethyl
    -0.06
    Short
    -0.06
    _BOOK
    -0.06
    _HP
    -0.06
    _geom
    -0.06
    POSITIVE LOGITS
     uranium
    0.08
     hexadecimal
    0.06
    воб
    0.06
    .DATA
    0.06
    dfunding
    0.06
     мик
    0.06
     Delegate
    0.06
     decision
    0.06
    509
    0.06
    чины
    0.06
    Act Density 0.024%

    No Known Activations