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

    Neuronpedia

    INDEX
    Explanations

    "Openings and beyond"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    숨
    0.32
    ض
    0.30
    Erro
    0.29
    يتها
    0.29
     आद
    0.28
     कसोटी
    0.27
    ವಾರು
    0.27
    Bringing
    0.27
     العمل
    0.26
     বিষয়ে
    0.26
    POSITIVE LOGITS
    ular
    0.31
    設
    0.28
    ylvania
    0.28
     nik
    0.28
     Mp
    0.28
     fixe
    0.28
    uminação
    0.27
     case
    0.27
    icie
    0.27
     participants
    0.27
    Act Density 0.011%

    No Known Activations