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

    Neuronpedia

    INDEX
    Explanations

    Sentence structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PMI
    -0.09
     Belmont
    -0.08
     Horton
    -0.08
     Stockton
    -0.08
    .Paths
    -0.08
     vested
    -0.08
    瞬
    -0.07
     Harness
    -0.07
     Harmon
    -0.07
     Goldman
    -0.07
    POSITIVE LOGITS
     русском
    0.14
     україн
    0.13
     Portuguese
    0.12
     باللغة
    0.12
     Russian
    0.12
     Ukrainian
    0.12
    Spanish
    0.12
    中文
    0.12
     magyar
    0.12
    Portugu
    0.11
    Act Density 0.243%

    No Known Activations