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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, business names and trademarks.

    oai_token-act-pair · gemini-2.0-flash

    reviews and product descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -1.00
    TagMode
    -0.93
    WriteAttribute
    -0.85
    AddTagHelper
    -0.85
    rungsseite
    -0.82
    تقاوى
    -0.81
    RegistryLite
    -0.79
    Hochspringen
    -0.77
    TagHelper
    -0.76
    abestanden
    -0.75
    POSITIVE LOGITS
     multi
    0.52
     mobile
    0.50
     Type
    0.50
     Multi
    0.48
     G
    0.48
     System
    0.48
     large
    0.48
     P
    0.47
     Car
    0.46
     Super
    0.46
    Act Density 1.719%

    No Known Activations