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

    Neuronpedia

    INDEX
    Explanations

    Specific, individual

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بدون
    -0.07
     شکن
    -0.07
    Philadelphia
    -0.07
    ailand
    -0.07
     pottery
    -0.07
     Berlin
    -0.07
    Republicans
    -0.07
    页面存档备份
    -0.06
     }];↵↵
    -0.06
     quoted
    -0.06
    POSITIVE LOGITS
     ห
    0.06
    viol
    0.06
     cope
    0.06
     InternalEnumerator
    0.06
    -money
    0.06
     оч
    0.06
    iard
    0.06
     icy
    0.06
     ру
    0.06
     všechny
    0.06
    Act Density 0.076%

    No Known Activations