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

    Neuronpedia

    INDEX
    Explanations

    illegal content or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     якія
    0.28
    られました
    0.26
     screwed
    0.26
     interle
    0.26
    schemas
    0.26
    䚺
    0.26
     Ди
    0.25
     perturbed
    0.24
    lardı
    0.24
     디
    0.24
    POSITIVE LOGITS
    没有任何
    0.31
    তম
    0.30
    并且
    0.30
     orice
    0.29
     anytime
    0.29
    且
    0.29
    的原因
    0.29
    任何人
    0.28
    ！！！
    0.28
     qualunque
    0.28
    Act Density 0.019%

    No Known Activations