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

    Neuronpedia

    INDEX
    Explanations

    Alina, Alphon, Aldo, Albedo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    exclusive
    0.46
    ავი
    0.44
     exclusive
    0.41
    यची
    0.40
    Exclusive
    0.39
    之后
    0.38
    的事
    0.37
    atosis
    0.37
     हाइ
    0.37
     Pseud
    0.36
    POSITIVE LOGITS
     Zhu
    0.41
     impoverished
    0.39
     Leung
    0.38
     Zhou
    0.38
     अंदा
    0.38
     กม
    0.37
     ኮ
    0.37
    हालय
    0.37
     आरोप
    0.37
     rehab
    0.36
    Act Density 0.001%

    No Known Activations