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

    Neuronpedia

    INDEX
    Explanations

    python matplotlib pyplot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    0.75
     and
    0.71
     by
    0.70
    "
    0.67
     The
    0.66
    '
    0.64
    ↵
    0.64
     By
    0.63
    _
    0.62
     A
    0.60
    POSITIVE LOGITS
    TorpedoStore
    0.58
     nitrile
    0.57
    ggbb
    0.55
     simonsen
    0.55
    posaż
    0.54
    uyentes
    0.54
     ноги
    0.54
    deload
    0.54
     металли
    0.53
    куляр
    0.53
    Act Density 0.006%

    No Known Activations