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

    Neuronpedia

    INDEX
    Explanations

    android

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     XII
    -0.07
    .sess
    -0.07
     zaj
    -0.06
    AMED
    -0.06
    .metro
    -0.06
     wy
    -0.06
     Bowman
    -0.06
    ↵↵    ↵
    -0.06
    	center
    -0.06
    .ret
    -0.06
    POSITIVE LOGITS
     moh
    0.07
    炮
    0.06
    表示
    0.06
    .Db
    0.06
     فوق
    0.06
     Henrik
    0.06
    لام
    0.06
     прин
    0.06
    erp
    0.06
    progress
    0.06
    Act Density 0.004%

    No Known Activations