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

    Neuronpedia

    INDEX
    Explanations

    one-time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     하나의
    0.53
     하나
    0.52
     single
    0.50
     one
    0.49
    一つの
    0.49
     één
    0.48
     одной
    0.48
     few
    0.47
     SINGLE
    0.47
     одним
    0.47
    POSITIVE LOGITS
     dealings
    0.44
    time
    0.41
    мын
    0.39
     parties
    0.39
    note
    0.39
     તેને
    0.39
    ties
    0.38
    ຜະລິດຕະພັນ
    0.38
    📰
    0.38
     nito
    0.38
    Act Density 0.008%

    No Known Activations