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

    Neuronpedia

    INDEX
    Explanations

    get or make things work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Being
    0.58
     being
    0.50
    被
    0.50
     be
    0.49
    being
    0.49
    be
    0.49
    huana
    0.47
    ube
    0.46
    Being
    0.46
    rone
    0.45
    POSITIVE LOGITS
     rid
    0.62
     kutoka
    0.61
     from
    0.59
     от
    0.57
     получить
    0.56
     informazioni
    0.56
     hjälp
    0.55
     удоволь
    0.54
     từ
    0.54
     glimpses
    0.53
    Act Density 0.071%

    No Known Activations