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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and specific formatting characters used in code

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

    image loading and manipulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     strijd
    -0.53
     fiabilité
    -0.48
     vertrouwen
    -0.48
     appuntamento
    -0.48
     urusan
    -0.47
     autorización
    -0.47
     hodiny
    -0.47
    zwungen
    -0.46
    ถม
    -0.46
    Reprodução
    -0.46
    POSITIVE LOGITS
     imagery
    0.63
    ImageData
    0.59
     Imagery
    0.59
     Images
    0.57
     Image
    0.57
     imagen
    0.57
    Image
    0.56
     lenker
    0.54
     image
    0.54
    getImage
    0.53
    Act Density 0.011%

    No Known Activations