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

    Neuronpedia

    INDEX
    Explanations

    concepts related to layering and fashion

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

    layers and looks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     infeliz
    -0.39
    utuhkan
    -0.36
     poži
    -0.35
     rendement
    -0.34
     عرو
    -0.34
    ACIONAL
    -0.34
     preventivo
    -0.34
     éprou
    -0.34
     committee
    -0.33
     assets
    -0.33
    POSITIVE LOGITS
    XmlAccessType
    0.59
     peeking
    0.54
    bootstrapcdn
    0.49
     flaps
    0.48
     layering
    0.48
     muualla
    0.47
     cropped
    0.46
    loops
    0.45
     worn
    0.45
    jazz
    0.45
    Act Density 0.011%

    No Known Activations