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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CV
    -0.07
     Pest
    -0.07
    oneksi
    -0.07
     active
    -0.07
     fueled
    -0.06
    color
    -0.06
     Variation
    -0.06
    -fed
    -0.06
    levard
    -0.06
     之
    -0.06
    POSITIVE LOGITS
     khỏe
    0.07
    (posts
    0.07
    かに
    0.06
    .squareup
    0.06
    poons
    0.06
     نتیجه
    0.06
     좋아
    0.06
    屆
    0.06
     담
    0.06
    ються
    0.06
    Act Density 0.013%

    No Known Activations