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

    Neuronpedia

    INDEX
    Explanations

    image URLs and related attributes in document structures

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

    Image resizing or scaling

    np_acts-logits-general · gemini-2.0-flash

    image scale and fit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.70
     liệt
    -0.62
    RetentionPolicy
    -0.60
     propOrder
    -0.60
     незавершена
    -0.59
     åt
    -0.57
     visuals
    -0.54
     endblock
    -0.54
    Ārējās
    -0.54
    +#+
    -0.53
    POSITIVE LOGITS
     crop
    0.70
     cropped
    0.64
     cropping
    0.64
     BoxFit
    0.60
     Crop
    0.59
    SizeMode
    0.58
    TagMode
    0.58
     scaled
    0.57
     scale
    0.56
    Crop
    0.56
    Act Density 0.145%

    No Known Activations