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

    Neuronpedia

    INDEX
    Explanations

    structured lists or enumerations, especially those involving sequential points or categories

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

    Enumerations, often (i), (1), (a)

    np_acts-logits-general · gemini-2.0-flash

    enumerating points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    abestanden
    -0.62
    Vidite
    -0.60
     responsabilità
    -0.56
     décontract
    -0.53
    [toxicity=0]
    -0.52
     ويكيميديا
    -0.52
    adaptiveStyles
    -0.51
     trattano
    -0.51
     homotopy
    -0.49
     fonctionnalité
    -0.49
    POSITIVE LOGITS
    первых
    0.77
    tagHelperRunner
    0.64
    Източници
    0.58
     كومونز
    0.56
    pexpr
    0.55
     newBuilder
    0.55
    horabuena
    0.54
     تضيفلها
    0.53
     lenker
    0.53
    ffè
    0.53
    Act Density 0.354%

    No Known Activations