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

    Neuronpedia

    INDEX
    Explanations

    sequences or patterns indicating structural elements in a programming context

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

    Code followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BorderRadius
    -0.71
    VersionUID
    -0.66
    RectangleBorder
    -0.65
     BoxDecoration
    -0.65
    Autoritní
    -0.64
    SequentialGroup
    -0.62
     &___
    -0.60
    TagMode
    -0.59
     שוליים
    -0.58
    //});
    -0.58
    POSITIVE LOGITS
    parsedMessage
    0.56
     hinweg
    0.52
     itſelf
    0.46
     KCl
    0.45
    throws
    0.45
     prestazioni
    0.44
     nae
    0.43
     sult
    0.43
    ⇓
    0.43
    тория
    0.43
    Act Density 0.226%

    No Known Activations