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

    Neuronpedia

    INDEX
    Explanations

    -described

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     더욱
    -0.08
     lekker
    -0.07
    ponce
    -0.06
     Norte
    -0.06
    Laughs
    -0.06
    .pose
    -0.06
     artış
    -0.06
    ملة
    -0.06
     روستا
    -0.06
    相关
    -0.06
    POSITIVE LOGITS
    .sql
    0.07
    -first
    0.06
     vacation
    0.06
    _SOL
    0.06
    Thin
    0.06
     Known
    0.06
     con
    0.06
     exploited
    0.06
    (duration
    0.06
     constituted
    0.05
    Act Density 0.002%

    No Known Activations