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

    Neuronpedia

    INDEX
    Explanations

    intersectionality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quieras
    0.48
    蕲
    0.47
    基づ
    0.46
     }{\
    0.45
    આત
    0.44
     അന്വേഷ
    0.44
    कालय
    0.44
    手数料
    0.43
     мо
    0.42
     testaceis
    0.42
    POSITIVE LOGITS
    s
    0.60
    as
    0.59
    os
    0.59
    on
    0.55
    ar
    0.51
    or
    0.49
    est
    0.49
    om
    0.48
    erus
    0.47
    ต
    0.47
    Act Density 0.009%

    No Known Activations