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

    Neuronpedia

    INDEX
    Explanations

    ingredients/products

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cure
    -0.63
     insuffisamment
    -0.62
     soot
    -0.61
    Cure
    -0.59
     contextLoads
    -0.57
    ly
    -0.55
     chaff
    -0.54
     ulcers
    -0.52
     magma
    -0.52
     charts
    -0.52
    POSITIVE LOGITS
    зулта
    0.62
     enfans
    0.60
     caduta
    0.60
     aukš
    0.55
     vœux
    0.55
    putBoolean
    0.54
     moindre
    0.54
     الرياضيه
    0.54
     indisponible
    0.53
    #+#
    0.53
    Act Density 1.791%

    No Known Activations