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

    Neuronpedia

    INDEX
    Explanations

    time after an event

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ার্ভ
    0.49
    際に
    0.48
     ६
    0.46
    า
    0.46
    িয়ে
    0.45
    ताव
    0.45
    ing
    0.45
    湘
    0.44
     २४
    0.44
     ৩৪
    0.44
    POSITIVE LOGITS
    t
    0.47
    i
    0.47
     Schema
    0.40
     preserving
    0.40
    éges
    0.39
    sigmoid
    0.39
     its
    0.38
    l
    0.38
     semis
    0.37
     pubescent
    0.37
    Act Density 0.018%

    No Known Activations