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

    Neuronpedia

    INDEX
    Explanations

    segments of text that represent indentation or whitespace formatting

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

    code and programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.55
     defaultstate
    -0.48
     Honours
    -0.46
     InputDecoration
    -0.43
     honours
    -0.43
    endphp
    -0.40
    AxisAlignment
    -0.40
    AsUp
    -0.39
    __*/
    -0.38
    relativeTime
    -0.38
    POSITIVE LOGITS
    +:+
    0.53
     civiles
    0.50
    GenerationType
    0.50
     يتيمه
    0.49
    .*")]
    0.46
     civils
    0.45
     CIVIL
    0.45
     intptr
    0.45
     AGRE
    0.43
     języka
    0.42
    Act Density 0.018%

    No Known Activations