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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Nit
    -0.08
    /runtime
    -0.07
    洁
    -0.07
    าย
    -0.07
    锡
    -0.07
    筋
    -0.07
    冬
    -0.07
     waitFor
    -0.06
     Denis
    -0.06
     aerobic
    -0.06
    POSITIVE LOGITS
    [],↵
    0.07
     expectedResult
    0.07
    .Currency
    0.07
    赢家
    0.07
     wenn
    0.07
    กลาย
    0.07
    perm
    0.07
     traction
    0.06
    (FLAGS
    0.06
    ADDR
    0.06
    Act Density 0.133%

    No Known Activations