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

    Neuronpedia

    INDEX
    Explanations

    benchmarks or tests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     insight
    -0.07
     plat
    -0.07
    Ż
    -0.07
    ảnh
    -0.07
     ary
    -0.07
     insights
    -0.07
    μορ
    -0.07
    東京都
    -0.07
    [element
    -0.07
     vault
    -0.07
    POSITIVE LOGITS
    	progress
    0.08
     ছাত্র
    0.08
    _progress
    0.08
    ോർ
    0.08
    _gene
    0.07
     दृ
    0.07
     querendo
    0.07
     kuts
    0.07
     progresso
    0.07
     Seeking
    0.07
    Act Density 0.008%

    No Known Activations