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

    Neuronpedia

    INDEX
    Explanations

    instances of specific number patterns or sequences

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

    Followed by a question mark or semicolon

    np_acts-logits-general · gemini-2.0-flash

    Hartmut Kaiser authorship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -1.05
    ?')
    -0.81
    TagMode
    -0.76
    fjspx
    -0.71
    ？】
    -0.71
    SequentialGroup
    -0.70
    prepareStatement
    -0.67
     BoxDecoration
    -0.67
    ?”,
    -0.67
    ?',
    -0.65
    POSITIVE LOGITS
     Software
    0.66
    tvguidetime
    0.64
     <
    0.63
    Software
    0.62
    Coder
    0.59
    Code
    0.59
     Technology
    0.58
    code
    0.58
    0.57
     betweenstory
    0.57
    Act Density 0.315%
    No Known Activations