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

    Neuronpedia

    INDEX
    Explanations

    free

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     площади
    0.67
     hyster
    0.65
    rupole
    0.65
     gneiss
    0.62
    ائج
    0.61
     myopia
    0.60
    ស៊ី
    0.60
     পাকা
    0.60
    豌
    0.60
    뢰
    0.59
    POSITIVE LOGITS
     free
    2.63
    Free
    2.38
    free
    2.31
     Free
    2.30
     FREE
    2.09
    FREE
    1.92
     libre
    1.82
     vrije
    1.81
    自由
    1.76
     gratis
    1.74
    Act Density 0.100%

    No Known Activations