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

    Neuronpedia

    INDEX
    Explanations

    parallel, division, integer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     className
    0.43
     inquiet
    0.40
     realizations
    0.40
     life
    0.38
    JPEG
    0.38
     Poincaré
    0.37
     Eti
    0.37
     intellectual
    0.37
    uvi
    0.37
     통
    0.36
    POSITIVE LOGITS
     raíz
    0.39
     trùng
    0.39
    軫
    0.39
     Odds
    0.38
    スト
    0.38
     αφού
    0.38
     саме
    0.36
    িম
    0.36
    识别
    0.36
    互相
    0.36
    Act Density 0.001%

    No Known Activations