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

    Neuronpedia

    INDEX
    Explanations

    elements of code structure in programming languages

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

    Code or configuration snippets using underscores

    np_acts-logits-general · gemini-2.0-flash

    code properties and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    D
    -0.67
    -
    -0.65
    R
    -0.63
    U
    -0.62
    S
    -0.62
    F
    -0.61
    O
    -0.57
    L
    -0.57
    //
    -0.57
    2
    -0.57
    POSITIVE LOGITS
     AssemblyCulture
    0.93
    ########.
    0.91
     nakalista
    0.86
    SBATCH
    0.84
    ientí
    0.83
    +#+#
    0.82
     Мексичка
    0.81
     saites
    0.81
     Савезне
    0.81
    LabelTagHelper
    0.80
    Act Density 0.262%

    No Known Activations