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

    Neuronpedia

    INDEX
    Explanations

    nested structures, particularly lists and tuples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code structures and specific names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pfund
    -0.33
    vfill
    -0.32
    hidupan
    -0.31
    </tfoot>
    -0.31
     đấy
    -0.30
     nawr
    -0.30
    endif
    -0.30
     além
    -0.29
    anskje
    -0.29
    پیوند
    -0.28
    POSITIVE LOGITS
    =('
    0.73
    ('
    0.72
    :✨
    0.71
    (('
    0.71
     ('
    0.69
     transfieras
    0.68
    SequentialGroup
    0.66
    (("
    0.64
     autorytatywna
    0.63
     ['
    0.61
    Act Density 0.001%

    No Known Activations