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

    Neuronpedia

    INDEX
    Explanations

    Patents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    昙
    -0.07
     outFile
    -0.07
    見え
    -0.07
     redirected
    -0.07
     sond
    -0.07
    го
    -0.07
     contacted
    -0.07
    不同类型
    -0.06
    imit
    -0.06
    POSITIVE LOGITS
     Cain
    0.08
    打架
    0.07
    scene
    0.07
     unarmed
    0.07
     builders
    0.07
    lemma
    0.06
     כאן
    0.06
     SOLUTION
    0.06
    quez
    0.06
    聋
    0.06
    Act Density 0.054%

    No Known Activations