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

    Neuronpedia

    INDEX
    Explanations

    complex structured code snippets and references within programming contexts

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

    Code snippets/diffs/non-English words

    np_acts-logits-general · gemini-2.0-flash

    code diffs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    protoimpl
    -0.80
     GenerationType
    -0.79
    Collegamenti
    -0.73
    ArrowToggle
    -0.72
     AssemblyCulture
    -0.70
    DotNetBar
    -0.69
     صوتيه
    -0.67
    ViewImports
    -0.65
    IsPostBack
    -0.65
    KEYCODE
    -0.65
    POSITIVE LOGITS
    [toxicity=0]
    0.64
     Réponses
    0.61
     οποίο
    0.57
    hline
    0.53
    0.53
     оригіналу
    0.53
     öns
    0.52
    '].'
    0.52
    bbene
    0.51
    ↵↵↵↵↵
    0.50
    Act Density 0.058%

    No Known Activations