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

    Neuronpedia

    INDEX
    Explanations

    CORS configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ER
    1.64
    狱
    1.36
     数据
    1.28
     pamoja
    1.28
    bar
    1.27
     chén
    1.27
    ούς
    1.27
     bains
    1.23
    t
    1.22
    ﺃ
    1.22
    POSITIVE LOGITS
    ن
    1.93
    нской
    1.66
    いて
    1.44
    nte
    1.44
    يج
    1.41
    н
    1.39
    ра
    1.38
    ের
    1.37
    ро
    1.37
     CORPER
    1.36
    Act Density 0.001%

    No Known Activations