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

    Neuronpedia

    INDEX
    Explanations

    script

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Size
    -0.07
     현
    -0.07
     BJ
    -0.06
    views
    -0.06
    .uri
    -0.06
    िं
    -0.06
    DSP
    -0.06
     Period
    -0.06
     diaper
    -0.06
     국
    -0.06
    POSITIVE LOGITS
     Rivera
    0.07
    .CommandType
    0.07
    estruct
    0.07
    urement
    0.06
     Coupons
    0.06
     afterward
    0.06
    かった
    0.06
    GC
    0.06
     pan
    0.06
    tparam
    0.06
    Act Density 0.006%

    No Known Activations