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

    Neuronpedia

    INDEX
    Explanations

    quart

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.08
     Costume
    -0.07
     prost
    -0.07
    .actions
    -0.07
     الأمم
    -0.07
    _passwd
    -0.06
     aggressively
    -0.06
     Comedy
    -0.06
     losing
    -0.06
    “These
    -0.06
    POSITIVE LOGITS
     Fixed
    0.07
    榰
    0.07
     {});↵↵
    0.07
    Gram
    0.06
    𫍣
    0.06
     Database
    0.06
    烟花爆
    0.06
    数目
    0.06
    钢板
    0.06
    power
    0.06
    Act Density 0.006%

    No Known Activations