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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     порушення
    -0.08
    또
    -0.07
     entrepreneur
    -0.07
     olmaz
    -0.07
     NAT
    -0.07
     hefty
    -0.07
     proble
    -0.06
     되
    -0.06
    .Pod
    -0.06
     hari
    -0.06
    POSITIVE LOGITS
    ?>
↵
    0.09
    %;
↵
    0.06
    poons
    0.06
     %(
    0.06
    _concat
    0.06
    Chart
    0.06
     AA
    0.06
    hythm
    0.06
     humorous
    0.06
    _comb
    0.06
    Act Density 0.000%

    No Known Activations