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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    elocity
    -0.07
    imestamp
    -0.06
    atype
    -0.06
    =_('
    -0.06
    uels
    -0.06
     birlikte
    -0.06
    edelta
    -0.06
    expr
    -0.06
     zda
    -0.06
    ounter
    -0.06
    POSITIVE LOGITS
     safest
    0.07
    153
    0.07
    PullParser
    0.07
    官网
    0.06
    *out
    0.06
    .UltraWin
    0.06
    #SBATCH
    0.06
     harmful
    0.06
     것도
    0.06
    电脑
    0.06
    Act Density 0.000%

    No Known Activations