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

    Neuronpedia

    INDEX
    Explanations

    Ok

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    唝
    -0.08
     boolean
    -0.07
    IVER
    -0.07
    zu
    -0.07
     NRL
    -0.07
     tooth
    -0.07
    쿅
    -0.07
    YS
    -0.07
    DDevice
    -0.07
     homepage
    -0.07
    POSITIVE LOGITS
     OkHttpClient
    0.07
    겥
    0.07
    高雄
    0.07
    願
    0.07
     שו
    0.07
    哪一个
    0.06
    .reporting
    0.06
    גבול
    0.06
                   ↵
    0.06
    続けて
    0.06
    Act Density 0.008%

    No Known Activations