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

    Neuronpedia

    INDEX
    Explanations

    at any time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     various
    0.43
     copi
    0.41
    色々
    0.40
    いろいろ
    0.39
     transposed
    0.38
    命运
    0.38
     avoid
    0.38
     diverses
    0.38
    一定的
    0.38
     Tina
    0.37
    POSITIVE LOGITS
     anytime
    2.38
     Anytime
    2.11
    随时
    2.02
     jederzeit
    1.95
     언제
    1.62
    いつでも
    1.62
     whenever
    1.34
     Whenever
    1.30
    whenever
    1.30
    Whenever
    1.27
    Act Density 0.022%

    No Known Activations