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

    Neuronpedia

    INDEX
    Explanations

    code structure elements, particularly those related to data serialization formats like JSON

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

    Code snippets; backticks

    np_acts-logits-general · gemini-2.0-flash

    code and data structure syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    -0.96
     Ratna
    -0.91
    ••••
    -0.90
    •••
    -0.84
     Meksiku
    -0.81
     Infórmanos
    -0.80
    erad
    -0.80
    avajillas
    -0.79
    gamesh
    -0.79
     Stande
    -0.78
    POSITIVE LOGITS
    =`
    1.41
    :`
    1.40
     `
    1.37
     (`
    1.34
    .`
    1.31
    (`
    1.28
    {`
    1.25
     `<
    1.24
     `/
    1.15
    >`
    1.13
    Act Density 0.336%

    No Known Activations