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

    Neuronpedia

    INDEX
    Explanations

    import and use statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endaftaran
    0.68
     депута
    0.67
    zeichen
    0.67
    τηση
    0.67
    тать
    0.66
     Administración
    0.63
     trại
    0.63
     Chestnut
    0.63
     программу
    0.61
    ว
    0.61
    POSITIVE LOGITS
     Ert
    0.70
     চলিয়া
    0.64
    埃
    0.63
     has
    0.63
     consistently
    0.62
     insign
    0.60
     zoos
    0.59
     loafers
    0.59
     due
    0.59
     irregularity
    0.59
    Act Density 0.012%

    No Known Activations