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

    Neuronpedia

    INDEX
    Explanations

    list items and ingredients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     synthesize
    0.50
     olefins
    0.44
     squamous
    0.44
     histological
    0.42
     shrimps
    0.42
     quadrupole
    0.42
     fgets
    0.41
     성
    0.40
     fuentes
    0.40
     treatises
    0.40
    POSITIVE LOGITS
     élevé
    0.46
    Service
    0.46
    ce
    0.46
     Service
    0.44
    En
    0.43
    ée
    0.43
    Ce
    0.43
    endroit
    0.43
     intéressant
    0.42
    Car
    0.41
    Act Density 0.001%

    No Known Activations