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

    Neuronpedia

    INDEX
    Explanations

    independence declared

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝗨
    0.56
    였습니다
    0.52
     установки
    0.49
    टी
    0.46
     제작
    0.46
    ائیگی
    0.46
    ofluorescence
    0.46
     کرنے
    0.45
    geven
    0.45
    arına
    0.44
    POSITIVE LOGITS
     Section
    0.51
     \
    0.48
     ome
    0.47
     `
    0.47
     x
    0.46
     _
    0.46
     is
    0.46
     Mead
    0.46
     can
    0.45
     both
    0.45
    Act Density 0.015%

    No Known Activations