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

    Neuronpedia

    INDEX
    Explanations

    player actions and capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝙞
    1.43
    ة
    1.39
    ת
    1.37
     boomers
    1.23
     apoptotic
    1.22
    йки
    1.22
     livery
    1.19
    哮
    1.18
     siitä
    1.17
     wept
    1.17
    POSITIVE LOGITS
     successfully
    1.01
    0.92
     behalf
    0.90
     vzd
    0.90
     असम
    0.90
     Fifty
    0.90
     было
    0.89
     дея
    0.89
    [-\
    0.88
     указыва
    0.88
    Act Density 0.000%

    No Known Activations