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

    Neuronpedia

    INDEX
    Explanations

    elements related to color and finish in product descriptions

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

    Colors

    np_acts-logits-general · gemini-2.0-flash

    color descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.75
     متعلقه
    -0.71
    DockStyle
    -0.67
     kasarigan
    -0.62
    ⓧ
    -0.60
     dysplasia
    -0.59
     الرياضيه
    -0.57
    diali
    -0.57
     дописавши
    -0.57
     betweenstory
    -0.55
    POSITIVE LOGITS
     black
    1.55
     white
    1.52
     gray
    1.30
     grey
    1.27
    white
    1.24
    black
    1.22
     blue
    1.22
     brown
    1.15
     yellow
    1.12
     green
    1.06
    Act Density 0.171%

    No Known Activations