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

    Neuronpedia

    INDEX
    Explanations

    multi-lingual completions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    3
    0.49
    5
    0.49
     Fujita
    0.49
    ^{*}=\
    0.46
     Verme
    0.46
    ˘
    0.46
     Avoiding
    0.45
    ավոր
    0.44
    🙍
    0.44
    LevelLinking
    0.44
    POSITIVE LOGITS
    នូវ
    0.64
    る
    0.57
    ла
    0.55
    ும்
    0.50
     obl
    0.48
    ிறது
    0.46
    q
    0.46
     dynamic
    0.45
     commencement
    0.45
     commod
    0.44
    Act Density 0.017%

    No Known Activations