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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming syntax and structure in code

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

    Code snippets or math symbols

    np_acts-logits-general · gemini-2.0-flash

    code punctuation and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     JpaRepository
    -0.80
    kloped
    -0.76
    IsMutable
    -0.73
    Chham
    -0.70
     Efq
    -0.68
    StructEnd
    -0.67
     ſind
    -0.66
    ſelf
    -0.65
     ſche
    -0.64
     >",
    -0.63
    POSITIVE LOGITS
    ↵↵
    0.76
    ↵
    0.56
    .
    0.55
    ↵↵↵
    0.51
     مرئيه
    0.47
    isRequired
    0.47
    ,
    0.45
    </tr>
    0.43
    ;
    0.43
    TagHelper
    0.43
    Act Density 0.013%

    No Known Activations