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

    Neuronpedia

    INDEX
    Explanations

    categories and related navigation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اق
    0.65
     pele
    0.61
    ైనా
    0.57
     настро
    0.57
     nurturing
    0.56
     CEF
    0.55
     moelle
    0.55
     américaine
    0.54
     myeloma
    0.54
     બા
    0.53
    POSITIVE LOGITS
    u
    0.91
    i
    0.71
    w
    0.71
    p
    0.70
    l
    0.64
    r
    0.63
     for
    0.62
    urbation
    0.59
    iidae
    0.59
    walkers
    0.56
    Act Density 0.006%

    No Known Activations