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

    Neuronpedia

    INDEX
    Explanations

    ideas and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     நீங்கள்
    0.24
    lensFlare
    0.24
    you
    0.24
     شما
    0.22
     sputtered
    0.22
    )\,
    0.22
     frowned
    0.21
     Nobody
    0.21
     crept
    0.21
    N
    0.21
    POSITIVE LOGITS
    us
    0.26
     and
    0.25
     interpersonal
    0.24
     socioeconomic
    0.22
    posição
    0.22
    ing
    0.22
    duction
    0.21
    пределение
    0.21
    HIP
    0.21
     affordability
    0.21
    Act Density 0.396%

    No Known Activations