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

    Neuronpedia

    INDEX
    Explanations

    code structure elements such as function declarations and control flow statements

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

    Code snippets or programming syntax

    np_acts-logits-general · gemini-2.0-flash

    javascript code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     int
    -0.62
    SequentialGroup
    -0.61
    int
    -0.58
    enumi
    -0.55
     Systems
    -0.53
     System
    -0.52
    ."—
    -0.52
    XmlEnum
    -0.52
    AccessorTable
    -0.52
    :#
    -0.51
    POSITIVE LOGITS
    console
    1.31
     console
    1.19
    let
    0.94
    const
    0.90
     let
    0.88
     const
    0.87
    setTimeout
    0.82
     `${
    0.81
    (`${
    0.76
     !==
    0.76
    Act Density 0.096%

    No Known Activations