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

    Neuronpedia

    INDEX
    Explanations

    opening and closing curly braces in programming code

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

    Starts a turn

    np_acts-logits-general · gemini-2.0-flash

    code and programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagext
    -0.48
    EndContext
    -0.43
     betweenstory
    -0.42
     ModelRenderer
    -0.40
    InvalidProtocol
    -0.40
    +#+#
    -0.39
    parseColor
    -0.38
    InputTagHelper
    -0.34
    transQ
    -0.34
    borderFill
    -0.33
    POSITIVE LOGITS
     Remy
    0.60
    ⟬
    0.60
    ={({
    0.59
     تضيفلها
    0.58
    lectic
    0.57
    ograft
    0.57
     Pauli
    0.57
     import
    0.57
    rometers
    0.57
    BeginInit
    0.56
    Act Density 0.005%

    No Known Activations