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

    Neuronpedia

    INDEX
    Explanations

    course outline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iv
    1.77
    cotton
    1.72
    ra
    1.71
    de
    1.67
    transport
    1.63
    cutaneous
    1.58
    <0xA7>
    1.57
    orthodox
    1.55
     Territory
    1.52
    og
    1.51
    POSITIVE LOGITS
    ся
    2.08
    ний
    1.98
    ن
    1.95
    tedir
    1.89
    сть
    1.84
    ться
    1.82
    летия
    1.66
     hiyo
    1.64
    殄
    1.64
    توا
    1.63
    Act Density 0.009%

    No Known Activations