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

    Neuronpedia

    INDEX
    Explanations

    approaches the, common, worsen, erasing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.51
    ,
    0.49
    ;
    0.48
    ?
    0.43
    er
    0.41
     scape
    0.40
    ్
    0.40
    a
    0.40
    kenalkan
    0.39
    つけた
    0.39
    POSITIVE LOGITS
     یو
    0.50
     пул
    0.50
     између
    0.49
     humide
    0.48
     नीड
    0.48
     будут
    0.47
     avrà
    0.47
     onları
    0.46
     Combustion
    0.46
     மூ
    0.45
    Act Density 0.002%

    No Known Activations