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

    Neuronpedia

    INDEX
    Explanations

    Old, initial, very, scientists, unwanted, accurate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noviembre
    0.40
     ноябре
    0.40
    nova
    0.39
    漪
    0.39
     yin
    0.38
    ȇ
    0.38
    ೊಂದ
    0.38
     NOVEMBER
    0.38
    ﭜ
    0.38
    สัมพันธ์
    0.38
    POSITIVE LOGITS
    ep
    0.41
    奂
    0.39
    鳧
    0.38
    奐
    0.38
     Ep
    0.38
    RICT
    0.38
    epe
    0.37
    󠁬
    0.37
    acqu
    0.37
    uate
    0.36
    Act Density 0.000%

    No Known Activations