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

    Neuronpedia

    INDEX
    Explanations

    any or all numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    多种
    0.41
     меч
    0.41
    Rés
    0.40
    েশের
    0.40
    제품
    0.40
    淀
    0.39
    多家
    0.39
     линий
    0.39
     мощность
    0.39
    рия
    0.38
    POSITIVE LOGITS
     cualquier
    0.59
     qualquer
    0.55
     qualunque
    0.50
     dowol
    0.49
     any
    0.48
    任何
    0.47
     orice
    0.46
     যেকোন
    0.46
     любого
    0.46
     любых
    0.46
    Act Density 0.042%

    No Known Activations