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

    Neuronpedia

    INDEX
    Explanations

    terms related to pixel attributes or measurements in images

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

    pixels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     general
    -0.40
    exact
    -0.39
     under
    -0.38
     exact
    -0.38
     plans
    -0.37
    Bronnen
    -0.35
     strict
    -0.34
     a
    -0.34
     set
    -0.34
     other
    -0.34
    POSITIVE LOGITS
     pixels
    1.94
    pixels
    1.78
    Pixels
    1.67
     Pixels
    1.54
    ixels
    0.90
    ctrons
    0.89
    像素
    0.81
     follicles
    0.73
    clicks
    0.72
     electrons
    0.71
    Act Density 0.008%

    No Known Activations