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

    Neuronpedia

    INDEX
    Explanations

    JavaScript function definitions and structural elements within code

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

    Code or programming-related text

    np_acts-logits-general · gemini-2.0-flash

    javascript code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]?.
    -0.71
    formik
    -0.67
    dataclass
    -0.67
     [...
    -0.64
    GenerationType
    -0.64
     `${
    -0.61
     constexpr
    -0.61
    kloped
    -0.60
     $"{
    -0.60
    uxxxx
    -0.60
    POSITIVE LOGITS
     $.
    0.73
     Backbone
    0.69
    Backbone
    0.65
     Unders
    0.61
     extend
    0.60
    .$.
    0.59
     ($.
    0.59
    ($.
    0.57
     $,
    0.56
     _.
    0.55
    Act Density 0.445%

    No Known Activations