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

    Neuronpedia

    INDEX
    Explanations

    method calls and function definitions in programming code

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

    Follows a period, underscore, or bracket

    np_acts-logits-general · gemini-2.0-flash

    setting properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -0.68
     Hopf
    -0.66
     autorytatywna
    -0.66
    bootstrapcdn
    -0.65
    DockStyle
    -0.65
    ագրություններ
    -0.61
    esgue
    -0.61
     виправивши
    -0.61
     Bessel
    -0.60
     sinuses
    -0.60
    POSITIVE LOGITS
    #![
    0.57
     rank
    0.57
     max
    0.56
    igue
    0.52
    yor
    0.51
    __["
    0.50
     maximum
    0.49
    行動
    0.49
     charge
    0.49
    звание
    0.49
    Act Density 0.112%

    No Known Activations