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

    Neuronpedia

    INDEX
    Explanations

    footnote

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]}$.
    0.64
    არს
    0.61
     पता
    0.60
    \
    0.59
     épaules
    0.57
    ुए
    0.57
     পুক
    0.56
    ésére
    0.56
    ricular
    0.54
    ungnya
    0.54
    POSITIVE LOGITS
    as
    1.07
    at
    0.83
     (
    0.71
    ด
    0.66
    น
    0.65
     as
    0.64
    н
    0.63
     Been
    0.61
     courtes
    0.60
    ↵
    0.58
    Act Density 0.001%

    No Known Activations