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

    Neuronpedia

    INDEX
    Explanations

    code statements ending in punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     toxicology
    0.57
     Nietzsche
    0.56
     nuanced
    0.56
     Bernoulli
    0.55
     withered
    0.55
     Python
    0.54
     Nana
    0.54
     Kiwi
    0.53
     juniper
    0.52
     codified
    0.52
    POSITIVE LOGITS
    ().
    0.95
    ._
    0.93
    !.
    0.91
    .
    0.90
    !!.
    0.86
    ->
    0.83
    ?.
    0.79
    .<
    0.79
    .__
    0.77
    的
    0.74
    Act Density 0.287%

    No Known Activations