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

    Neuronpedia

    INDEX
    Explanations

    technical discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lässt
    -0.06
    近
    -0.06
    asta
    -0.06
     culpa
    -0.06
     Depot
    -0.06
    .Actions
    -0.06
     करव
    -0.06
    umas
    -0.06
     δι
    -0.06
     люди
    -0.06
    POSITIVE LOGITS
     /(
    0.07
    乂
    0.07
    _live
    0.06
    상위
    0.06
    -common
    0.06
     универ
    0.06
    leigh
    0.06
     preg
    0.06
    Rob
    0.06
     V
    0.06
    Act Density 0.060%

    No Known Activations