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

    Neuronpedia

    INDEX
    Explanations

    place in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     каттоо
    1.06
     чыныгы
    0.91
    rawberry
    0.91
    urring
    0.91
    ensione
    0.90
     мыкты
    0.89
     mettere
    0.89
    ukiy
    0.89
     jornada
    0.88
    샨
    0.88
    POSITIVE LOGITS
    （
    0.88
     ў
    0.79
    κών
    0.79
     scrutinized
    0.74
    、
    0.71
    <>(
    0.71
    。
    0.70
    сиона
    0.69
    籍
    0.69
     peek
    0.68
    Act Density 0.001%

    No Known Activations