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

    Neuronpedia

    INDEX
    Explanations

    purpose or outcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    res
    0.23
    ”。
    0.21
    $.
    0.21
    $\
    0.20
    where
    0.20
    。
    0.20
    (),
    0.20
    j
    0.20
    $
    0.20
    ========
    0.20
    POSITIVE LOGITS
    在于
    0.28
     utilizzo
    0.27
    នៃការ
    0.25
     onus
    0.25
    ът
    0.24
     avem
    0.24
     pessoal
    0.23
     está
    0.23
     давление
    0.23
     distribuir
    0.23
    Act Density 0.470%

    No Known Activations