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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deserted
    -0.06
     MODULE
    -0.06
    ausible
    -0.06
     отдель
    -0.06
     Dense
    -0.06
    .method
    -0.06
    .Ent
    -0.06
     mutlak
    -0.06
    uD
    -0.06
    ores
    -0.06
    POSITIVE LOGITS
    :↵↵↵
    0.07
    設計
    0.07
    iaz
    0.07
    ...,
    0.06
     nemoh
    0.06
     ---
    0.06
    sehen
    0.06
    .↵↵↵↵↵↵
    0.06
     бух
    0.06
     Manip
    0.06
    Act Density 0.023%

    No Known Activations