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

    Neuronpedia

    INDEX
    Explanations

    index

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jeep
    -0.06
     millet
    -0.06
     Glasgow
    -0.06
     Scarlett
    -0.06
     لت
    -0.06
    กต
    -0.06
    ستان
    -0.06
    (annotation
    -0.06
     Bolton
    -0.06
    ’ta
    -0.06
    POSITIVE LOGITS
     index
    0.08
    dex
    0.07
     Index
    0.07
    indices
    0.07
     ifdef
    0.06
     matrix
    0.06
    خي
    0.06
     vzdál
    0.06
    Issues
    0.06
    (library
    0.06
    Act Density 0.002%

    No Known Activations