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

    Neuronpedia

    INDEX
    Explanations

    rude and related words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    腃
    0.47
     Nobody
    0.44
     pursuing
    0.43
    ləşdir
    0.42
    JUNE
    0.38
    Nobody
    0.37
    前景
    0.37
     Likewise
    0.37
    انون
    0.37
    defineProperty
    0.36
    POSITIVE LOGITS
     rud
    1.00
     rude
    0.95
    Rud
    0.87
     Rud
    0.80
    rud
    0.74
    rude
    0.74
     Rude
    0.70
     rudimentary
    0.67
     RUD
    0.65
     awakening
    0.64
    Act Density 0.002%

    No Known Activations