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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bean
    -0.08
    accumulate
    -0.07
    .Maybe
    -0.07
     native
    -0.07
    veal
    -0.06
     junk
    -0.06
    =@
    -0.06
     sod
    -0.06
     Она
    -0.06
     derive
    -0.06
    POSITIVE LOGITS
    哟
    0.06
     privileges
    0.06
    RGB
    0.06
    队伍建设
    0.06
     فقط
    0.06
    _processed
    0.06
     integer
    0.06
    团长
    0.06
     Tempo
    0.06
    ⊨
    0.06
    Act Density 0.002%

    No Known Activations