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

    Neuronpedia

    INDEX
    Explanations

    game, print, or mv

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    א
    1.13
    Firefox
    0.98
    м
    0.98
    Pentru
    0.95
    Italia
    0.94
    ot
    0.94
    ır
    0.91
    م
    0.91
    af
    0.90
    Toplam
    0.89
    POSITIVE LOGITS
     retir
    0.91
     lottery
    0.79
     Dep
    0.78
     robin
    0.78
     Гра
    0.75
     adv
    0.72
    s
    0.72
     IME
    0.72
     Dow
    0.71
     Cov
    0.71
    Act Density 0.000%

    No Known Activations