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

    Neuronpedia

    INDEX
    Explanations

    assertions and conditional statements in discussions about programming or system functionality

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

    starting words of sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.69
     समीक्षाओं
    -0.60
     الرياضيه
    -0.59
    IndentedString
    -0.57
    الحياه
    -0.54
     arru
    -0.48
    الدراسه
    -0.48
     Voc
    -0.47
    Dış
    -0.47
    EndInit
    -0.46
    POSITIVE LOGITS
    setVerticalGroup
    0.50
    -------------</
    0.47
    WithIOException
    0.46
     betweenstory
    0.41
     kvinder
    0.40
    localctx
    0.38
    domésticos
    0.38
     clearly
    0.36
    UnknownFieldSet
    0.36
    rrggbb
    0.35
    Act Density 0.004%

    No Known Activations