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

    Neuronpedia

    INDEX
    Explanations

    the following word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     I
    0.58
    Header
    0.54
     for
    0.53
     SWOT
    0.52
    re
    0.51
     A
    0.51
    Error
    0.49
    Hook
    0.49
     you
    0.49
    ()
    0.49
    POSITIVE LOGITS
    h
    0.62
    ن
    0.62
    y
    0.59
    同じ
    0.55
    ا
    0.54
    ン
    0.52
    นาย
    0.52
    я
    0.51
    的
    0.50
    با
    0.49
    Act Density 0.094%

    No Known Activations