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

    Neuronpedia

    INDEX
    Explanations

    Molecular weights calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сценар
    -0.09
     helft
    -0.08
    орол
    -0.08
     сц
    -0.08
     acontecer
    -0.08
    ("="
    -0.08
    (Messages
    -0.08
    Themes
    -0.08
     लॉ
    -0.08
    אָר
    -0.08
    POSITIVE LOGITS
     తాజ
    0.10
     wikipedia
    0.10
    最新版
    0.10
     citing
    0.10
     textbooks
    0.09
    官网
    0.09
    最新
    0.09
     cited
    0.09
     accuracy
    0.09
     NASA
    0.08
    Act Density 0.010%

    No Known Activations