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

    Neuronpedia

    INDEX
    Explanations

    numerical values and significant quantities in various contexts

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

    numbers followed by units or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.50
    
    -0.47
     suaminya
    -0.44
     tranſ
    -0.42
     mergeFrom
    -0.42
    RegistryLite
    -0.42
    BeginContext
    -0.41
    isuus
    -0.41
    AutoModerator
    -0.39
     perſon
    -0.39
    POSITIVE LOGITS
     Paso
    0.50
    NewReader
    0.45
    ">//
    0.43
    PASO
    0.41
    geber
    0.41
    spitze
    0.40
     للمعارف
    0.40
    createClass
    0.39
     MainAxisSize
    0.39
     Dane
    0.38
    Act Density 0.003%

    No Known Activations