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

    Neuronpedia

    INDEX
    Explanations

    programming-related conditions and checks in code

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

    checking if something changed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setLabel
    -0.33
     DN
    -0.32
     Train
    -0.31
     setEmail
    -0.31
    printStackTrace
    -0.31
     train
    -0.31
    исленность
    -0.30
     Verb
    -0.30
     setTitle
    -0.29
    BeforeEach
    -0.29
    POSITIVE LOGITS
    Datuak
    0.62
    Rüyada
    0.59
     bürger
    0.56
     disambiguazione
    0.56
    enderror
    0.56
    󠁴
    0.56
    featureID
    0.55
    ParallelGroup
    0.55
     незавершена
    0.54
    Демографія
    0.53
    Act Density 0.115%

    No Known Activations