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

    Neuronpedia

    INDEX
    Explanations

    expressions of exclusivity or emphasis

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

    Katy Perry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __':
    -0.48
     torebka
    -0.43
    Cyfarwyddwr
    -0.41
    struttura
    -0.41
     dàng
    -0.41
     Geister
    -0.40
    __':
    -0.40
     суще
    -0.40
     riders
    -0.39
     ActionListener
    -0.39
    POSITIVE LOGITS
    parsedMessage
    0.62
    addPreferredGap
    0.49
    CppMethod
    0.44
     المعيارى
    0.44
    Hozzáférés
    0.44
    featureID
    0.44
     SwitchCompat
    0.42
     continúas
    0.42
    KommentareTeilen
    0.42
    固
    0.41
    Act Density 0.080%

    No Known Activations