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

    Neuronpedia

    INDEX
    Explanations

    should

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     temptation
    -0.07
     времен
    -0.07
     commitments
    -0.07
    -sample
    -0.06
     /(
    -0.06
     imply
    -0.06
     Variation
    -0.06
     normalization
    -0.06
     ultr
    -0.06
     variable
    -0.06
    POSITIVE LOGITS
    .itemId
    0.07
     indexPath
    0.07
    股份有限公司
    0.07
    (letter
    0.07
     Sparks
    0.07
    /groups
    0.06
    _TRNS
    0.06
    lanmıştır
    0.06
    Regardless
    0.06
     "}↵
    0.06
    Act Density 0.027%

    No Known Activations