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

    Neuronpedia

    INDEX
    Explanations

    happens, more, emotion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Câu
    0.49
    قتها
    0.43
    UPA
    0.40
     ప్రశ్న
    0.39
    Ⴝ
    0.39
    VENTION
    0.38
     mũ
    0.37
    قت
    0.36
     सवालों
    0.36
    Linking
    0.36
    POSITIVE LOGITS
     Shay
    0.40
     setImage
    0.38
     scrapes
    0.38
     collision
    0.38
     rollover
    0.38
     feedback
    0.37
    юр
    0.37
    timetable
    0.37
     montant
    0.37
    {\
    0.36
    Act Density 0.001%

    No Known Activations