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

    Neuronpedia

    INDEX
    Explanations

    aggregate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .JOptionPane
    -0.08
    cré
    -0.07
     sympathetic
    -0.07
    상담
    -0.07
    ﷻ
    -0.07
    💊
    -0.07
    פגע
    -0.07
    衩
    -0.07
     מן
    -0.07
    所能
    -0.06
    POSITIVE LOGITS
    Ro
    0.07
    (cl
    0.07
     Hydraulic
    0.07
     dropping
    0.07
     dress
    0.07
    这份
    0.07
     Audience
    0.06
    dish
    0.06
    魔术
    0.06
    ifique
    0.06
    Act Density 0.003%

    No Known Activations