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

    Neuronpedia

    INDEX
    Explanations

    minimalist style

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ar
    1.10
    in
    1.05
     as
    0.99
    し
    0.99
    ing
    0.98
     to
    0.97
    u
    0.97
    h
    0.97
    as
    0.96
    ड
    0.96
    POSITIVE LOGITS
     minimalist
    0.94
     minimalistic
    0.86
     Quellen
    0.85
    }$;
    0.84
     Kör
    0.80
     ያለው
    0.79
    ρές
    0.79
     然后
    0.78
    }$
    0.77
     براي
    0.77
    Act Density 0.005%

    No Known Activations