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

    Neuronpedia

    INDEX
    Explanations

    Core followed by data, graphics, ML, MIDI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    1.10
    ل
    1.06
    z
    0.96
    and
    0.86
    ো
    0.85
    ა
    0.84
    n
    0.77
    ન
    0.76
    на
    0.75
    ే
    0.72
    POSITIVE LOGITS
     is
    1.09
     of
    0.93
    0
    0.88
     it
    0.82
    ０
    0.73
     a
    0.71
     лишь
    0.71
    ่า
    0.70
     liés
    0.70
    \
    0.68
    Act Density 0.000%

    No Known Activations