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

    Neuronpedia

    INDEX
    Explanations

    variable declarations and definitions in code

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

    variable declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ImageContext
    -0.46
     varandra
    -0.45
    ⏜
    -0.42
     lebaran
    -0.41
     Bulan
    -0.41
     probado
    -0.41
    homonymie
    -0.40
     entregas
    -0.40
     escenarios
    -0.39
     Lingkungan
    -0.39
    POSITIVE LOGITS
    GEBURTSDATUM
    0.47
    DrawerToggle
    0.42
    VGND
    0.42
    férés
    0.41
    awtextra
    0.40
     تضيفلها
    0.40
     Janus
    0.40
    zzo
    0.38
     CURIAM
    0.38
    inaison
    0.37
    Act Density 0.012%

    No Known Activations