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

    Neuronpedia

    INDEX
    Explanations

    terms related to software development best practices and guidelines

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

    Critiques of code or practices

    np_acts-logits-general · gemini-2.0-flash

    undesirable software qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.64
    ThroughAttribute
    -0.54
     ویکی‌پدیای
    -0.51
    ChildScrollView
    -0.50
     sabbia
    -0.48
     ghiaccio
    -0.48
    StartTag
    -0.47
    Utiliz
    -0.46
    tirol
    -0.45
     svolge
    -0.45
    POSITIVE LOGITS
     invariants
    0.77
     للاسماء
    0.66
     corner
    0.60
    — 
    0.60
     unsound
    0.60
     invariant
    0.60
     orthogonal
    0.60
     brittle
    0.59
     correctness
    0.58
     designers
    0.57
    Act Density 1.146%

    No Known Activations