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

    Neuronpedia

    INDEX
    Explanations

    vary from state to person

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    0.68
    to
    0.66
    ें
    0.57
    িত
    0.55
    nama
    0.54
    𝐢
    0.53
    ed
    0.52
    िक
    0.52
    ن
    0.51
    ualitas
    0.50
    POSITIVE LOGITS
     iterations
    0.51
    ﻲ
    0.49
     Bessel
    0.47
     biosolids
    0.47
    angleOf
    0.46
     Bellev
    0.46
     naught
    0.45
    amins
    0.45
     угодно
    0.44
     freshen
    0.44
    Act Density 0.003%

    No Known Activations