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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "top" or variations of it, particularly in ranking contexts

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

    Following "Top" or a hyphen

    np_acts-logits-general · gemini-2.0-flash

    top followed by category or ranking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.64
    StoreMessageInfo
    -0.62
    Personensuche
    -0.59
    emang
    -0.58
     Exacts
    -0.57
    MockMvc
    -0.57
    AnchorStyles
    -0.57
    stanz
    -0.56
    AccessorTable
    -0.55
    PropertyChanging
    -0.52
    POSITIVE LOGITS
    notch
    1.00
     notch
    1.00
    most
    0.89
     tier
    0.86
     rated
    0.81
    flight
    0.79
    knot
    0.77
     priority
    0.75
    ically
    0.73
    secret
    0.73
    Act Density 0.076%

    No Known Activations