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

    Neuronpedia

    INDEX
    Explanations

    syntax elements and structure in code

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

    images and image paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -0.60
    /*
    -0.56
    новниш
    -0.53
    transQ
    -0.51
    省市镇
    -0.50
    Tembelea
    -0.48
    SBATCH
    -0.47
     campionato
    -0.47
    crm
    -0.47
     coaches
    -0.47
    POSITIVE LOGITS
     image
    1.16
     images
    1.11
    image
    1.01
     Images
    1.00
     Image
    1.00
     pictures
    0.96
     picture
    0.93
     imagen
    0.93
    Image
    0.93
     imagem
    0.90
    Act Density 0.051%

    No Known Activations