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
     FAILURE
    -0.07
    都很
    -0.07
    olvimento
    -0.07
     Engagement
    -0.07
     acompanh
    -0.07
     Directorate
    -0.07
    ยอม
    -0.07
    בוצע
    -0.07
    Amt
    -0.07
     Thinking
    -0.07
    POSITIVE LOGITS
    uctor
    0.08
    红包
    0.08
    .char
    0.07
     (('
    0.07
    垯
    0.07
    _sites
    0.07
    .internal
    0.07
     push
    0.07
    -car
    0.06
    Cas
    0.06
    Act Density 0.009%

    No Known Activations