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

    Neuronpedia

    INDEX
    Explanations

    copyright declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    with
    0.46
    when
    0.46
     vuonna
    0.46
     tahun
    0.46
     latach
    0.46
     October
    0.45
     october
    0.44
     વર્ષ
    0.43
    during
    0.43
     ১৯৯
    0.43
    POSITIVE LOGITS
     Kā
    0.41
     Mercury
    0.41
    អ្វី
    0.39
    Mercury
    0.38
     mercury
    0.38
     bolts
    0.38
    鹅
    0.37
     Hernández
    0.36
    桠
    0.36
    ።
    0.36
    Act Density 0.000%

    No Known Activations