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

    Neuronpedia

    INDEX
    Explanations

    descriptive attributes related to color and shape in biological contexts

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

    descriptive terms followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pelle
    -0.57
     person
    -0.52
    ovsk
    -0.51
    Lymp
    -0.51
    acrylamide
    -0.48
    δει
    -0.47
     bere
    -0.45
     commercial
    -0.45
    pleen
    -0.45
     الحم
    -0.45
    POSITIVE LOGITS
     للمعارف
    0.94
    0.81
     Viewed
    0.75
     scolaires
    0.75
    بوابة
    0.72
     juzgar
    0.71
     Roskov
    0.70
     lenker
    0.69
    +#+
    0.69
    DockStyle
    0.69
    Act Density 0.108%

    No Known Activations