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

    Neuronpedia

    INDEX
    Explanations

    areas or related categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     asunto
    0.38
     వరకు
    0.34
     అమలు
    0.34
    是一个
    0.33
     reaksi
    0.33
    戻
    0.33
    ۖ
    0.33
    وامل
    0.33
     mientras
    0.32
     plupart
    0.32
    POSITIVE LOGITS
     whose
    0.54
    /
    0.52
     within
    0.51
    pecific
    0.51
     της
    0.46
     in
    0.45
     of
    0.45
     throughout
    0.43
     또는
    0.42
     identified
    0.41
    Act Density 0.711%

    No Known Activations