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

    Neuronpedia

    INDEX
    Explanations

    phrases describing varying representations or perceptions of reality

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

    picture of a situation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vym
    -0.30
     Decorative
    -0.30
     colocado
    -0.29
     núcleos
    -0.29
    INTERVAL
    -0.28
     specially
    -0.28
    layın
    -0.28
    ifoli
    -0.28
    porque
    -0.28
     Bege
    -0.28
    POSITIVE LOGITS
     picture
    0.92
     Picture
    0.86
    picture
    0.81
     картина
    0.80
    Picture
    0.79
    ImageContext
    0.79
     portrait
    0.78
     PICTURE
    0.77
     εικό
    0.70
     карти
    0.68
    Act Density 0.024%

    No Known Activations