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

    Neuronpedia

    INDEX
    Explanations

    neighborhood perks and characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    1.17
    u
    1.08
    y
    1.01
    .
    1.00
    ä
    0.94
    ov
    0.93
    ів
    0.93
    می
    0.93
    4
    0.92
    हे
    0.90
    POSITIVE LOGITS
     aand
    1.09
    ۰
    1.07
    ală
    0.99
    -{
    0.98
     acabado
    0.98
     Ичиго
    0.97
     Aś
    0.94
     arrhyth
    0.92
     اللاعب
    0.90
     önce
    0.89
    Act Density 0.001%

    No Known Activations