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

    Neuronpedia

    INDEX
    Explanations

    huggingface library

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     darker
    -0.06
    ạnh
    -0.06
     polygons
    -0.06
     rents
    -0.06
     inflated
    -0.06
     كيف
    -0.06
     두
    -0.06
    移動
    -0.06
     calcul
    -0.06
     tense
    -0.05
    POSITIVE LOGITS
    !:
    0.07
     harb
    0.07
     acuerdo
    0.07
    -established
    0.07
     fem
    0.06
    (parse
    0.06
     ".",
    0.06
    .strip
    0.06
    ving
    0.06
    .assertTrue
    0.06
    Act Density 0.001%

    No Known Activations