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

    Neuronpedia

    INDEX
    Explanations

    combining into one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ando
    0.43
    ென்று
    0.42
     Modo
    0.42
     a
    0.42
     Primeiro
    0.41
    ossos
    0.40
    ตร
    0.40
     GridLayout
    0.40
    ado
    0.39
    ırm
    0.39
    POSITIVE LOGITS
     сообщение
    0.44
    нэт
    0.42
    報告
    0.42
    しっかり
    0.41
     dakkh
    0.41
     работо
    0.41
    船
    0.41
     представи
    0.40
    REPORT
    0.40
     রিপোর্ট
    0.39
    Act Density 0.036%

    No Known Activations