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

    Neuronpedia

    INDEX
    Explanations

    words starting with 'sh'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fal
    1.07
     care
    1.01
     seepage
    0.99
     isinstance
    0.97
     lir
    0.94
     salto
    0.93
     Marca
    0.93
     disp
    0.92
     Fecha
    0.91
     सांग
    0.91
    POSITIVE LOGITS
    anigans
    1.17
    赧
    1.04
    tered
    1.03
    된
    1.02
    ঘ্রই
    0.98
    faced
    0.98
    pherd
    0.97
    രിയായ
    0.97
    FormProvider
    0.97
    andoah
    0.96
    Act Density 0.170%

    No Known Activations