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

    Neuronpedia

    INDEX
    Explanations

    Lists specifying items, people, or positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rafa
    0.81
    Фу
    0.74
    ત્મ
    0.73
    Guitar
    0.72
     Seen
    0.72
    Owl
    0.71
    Ска
    0.71
    Ե
    0.70
    Sold
    0.70
     vamp
    0.69
    POSITIVE LOGITS
    an
    1.10
    et
    1.02
    ka
    1.02
    as
    0.99
    in
    0.97
    im
    0.96
    co
    0.96
    io
    0.96
    ou
    0.95
    ac
    0.93
    Act Density 0.000%

    No Known Activations