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

    Neuronpedia

    INDEX
    Explanations

    phrases that include the word "who" and other service-related terms

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

    clauses describing people's actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mejorado
    -0.42
     personnelles
    -0.41
    WebElementEntity
    -0.41
    protoimpl
    -0.40
     bellezza
    -0.40
    IBOutlet
    -0.40
    Pratique
    -0.39
     desem
    -0.38
    تقاوى
    -0.38
    ClInclude
    -0.38
    POSITIVE LOGITS
    ipients
    0.54
    wieś
    0.48
     InputDecoration
    0.46
    adaptiveStyles
    0.45
    paux
    0.45
    bz
    0.44
    Rüyada
    0.44
     nakalista
    0.44
     Sending
    0.43
     bz
    0.42
    Act Density 0.086%

    No Known Activations