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

    Neuronpedia

    INDEX
    Explanations

    things, concepts, or self-worth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gies
    0.50
    gulation
    0.50
    ügen
    0.48
    ith
    0.47
    .')
    0.46
    ptide
    0.46
    wirkungen
    0.44
    uft
    0.44
     présentant
    0.43
     tive
    0.42
    POSITIVE LOGITS
     хозяйства
    0.52
    選手
    0.47
     or
    0.44
     ګټ
    0.43
    생활
    0.42
    ्यक्रम
    0.42
     ಅಭ
    0.41
    大
    0.40
    시설
    0.38
    信息
    0.38
    Act Density 0.001%

    No Known Activations