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

    Neuronpedia

    INDEX
    Explanations

    compounds multiplicatively, sequentially

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     characterizes
    0.38
     cinqui
    0.38
    gypt
    0.37
    known
    0.37
     housings
    0.36
     определяет
    0.36
     whence
    0.36
     Nxa
    0.35
    岌
    0.35
     worldview
    0.35
    POSITIVE LOGITS
    љу
    0.41
    LAUNCH
    0.41
     रकम
    0.40
     transferred
    0.39
     रक्कम
    0.39
     relaunch
    0.39
     transferência
    0.38
    されない
    0.37
     reinstated
    0.37
     multiplicação
    0.36
    Act Density 0.001%

    No Known Activations