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

    Neuronpedia

    INDEX
    Explanations

    punctuation and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    of
    0.70
    4
    0.70
    5
    0.64
    AL
    0.61
     nightmare
    0.61
    lecting
    0.61
    2
    0.60
    :
    0.60
    ة
    0.60
     be
    0.59
    POSITIVE LOGITS
     Pemerintah
    0.61
    จาก
    0.59
    ها
    0.57
    คุณ
    0.55
    㳓
    0.53
     Sulf
    0.52
    羪
    0.52
     bạn
    0.51
     penuh
    0.51
     مشخص
    0.51
    Act Density 0.000%

    No Known Activations