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

    Neuronpedia

    INDEX
    Explanations

    various types of code delimiters and separators

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

    programming and url delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    active
    -0.41
    agio
    -0.39
    inc
    -0.39
    observe
    -0.38
    榄
    -0.38
    forEach
    -0.37
    agent
    -0.37
     Just
    -0.36
     sp
    -0.36
    ura
    -0.35
    POSITIVE LOGITS
     StatefulWidget
    2.42
    aarrggbb
    0.79
    AndEndTag
    0.67
     ProtoMessage
    0.63
     numberOfRows
    0.63
     AspNetCore
    0.60
    WithIOException
    0.57
     beginnetje
    0.56
     ModelExpression
    0.56
     يتيمه
    0.56
    Act Density 0.000%

    No Known Activations