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

    Neuronpedia

    INDEX
    Explanations

    and not a professional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ક્સ
    0.69
    Optical
    0.67
     ос
    0.65
    オペ
    0.65
     mys
    0.64
     여
    0.63
    薊
    0.63
    рабо
    0.62
    écies
    0.62
    andex
    0.62
    POSITIVE LOGITS
    ímica
    0.73
     pegatina
    0.72
    गुण
    0.70
    nunique
    0.70
     sinais
    0.69
     sobald
    0.69
     îm
    0.67
    %、
    0.65
     puberty
    0.65
    ￥
    0.64
    Act Density 0.005%

    No Known Activations