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

    Neuronpedia

    INDEX
    Explanations

    other variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Recently
    0.26
    特朗普
    0.25
    ᕋ
    0.25
    لا
    0.25
    মান
    0.25
    '।
    0.25
     motionProxy
    0.25
     Previously
    0.25
     Subsequent
    0.24
    িয়াল
    0.24
    POSITIVE LOGITS
     остальных
    0.32
     나머
    0.32
     остальные
    0.30
    curses
    0.28
     나머지
    0.27
    utf
    0.27
    徒歩
    0.26
     resten
    0.26
    緞
    0.26
    tudo
    0.26
    Act Density 0.103%

    No Known Activations