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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     záznam
    -0.08
     pré
    -0.06
    ữ
    -0.06
     billionaire
    -0.06
     importantes
    -0.06
     shard
    -0.06
     rarity
    -0.06
    یل
    -0.06
     choses
    -0.06
    hammer
    -0.06
    POSITIVE LOGITS
    采用
    0.07
    .lastIndexOf
    0.06
     fullest
    0.06
    Em
    0.06
     nominated
    0.06
    reating
    0.06
    =======
    0.06
    ､
    0.06
     Scre
    0.06
     подт
    0.06
    Act Density 0.000%

    No Known Activations