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

    Neuronpedia

    INDEX
    Explanations

    quotation mark followed by text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !</
    0.40
     எனப்படும்
    0.37
     ($\
    0.37
     செய்ய
    0.37
    ?</
    0.36
     (=
    0.36
     avoir
    0.35
     (~
    0.35
    భ
    0.34
     naught
    0.34
    POSITIVE LOGITS
     “[
    0.99
     “(
    0.96
     "...
    0.95
     “…
    0.95
     "[
    0.93
    ：“
    0.92
     “‘
    0.90
     "(
    0.89
     "'
    0.84
     "..
    0.84
    Act Density 0.122%

    No Known Activations