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

    Neuronpedia

    INDEX
    Explanations

    Academic affiliations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Deck
    -0.07
     ingredient
    -0.07
    (Path
    -0.07
     організації
    -0.07
     protocols
    -0.06
    (Settings
    -0.06
    adratic
    -0.06
    πι
    -0.06
     landscapes
    -0.06
     rebuild
    -0.06
    POSITIVE LOGITS
    _Config
    0.07
     possessed
    0.06
     RectTransform
    0.06
    금
    0.06
    ای
    0.06
    efault
    0.06
     longing
    0.06
    imore
    0.06
     taxable
    0.06
     모르
    0.06
    Act Density 0.005%

    No Known Activations