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

    Neuronpedia

    INDEX
    Explanations

    algorithms like Marquardt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     últimas
    0.61
    enciais
    0.61
    مني
    0.60
     Vuitton
    0.59
     féri
    0.58
    रोना
    0.57
    upakan
    0.57
    昛
    0.57
    䢀
    0.57
    rägt
    0.57
    POSITIVE LOGITS
    -
    0.75
    ↵
    0.72
    /
    0.64
     systems
    0.61
     Systems
    0.57
    1
    0.55
    esque
    0.54
     Type
    0.54
    '
    0.52
    ・
    0.52
    Act Density 0.001%

    No Known Activations