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

    Neuronpedia

    INDEX
    Explanations

    helpful

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    رياضي
    -0.08
    允
    -0.07
    您同意
    -0.07
    การแสดง
    -0.07
    تكنولوجيا
    -0.06
    依旧是
    -0.06
    复杂
    -0.06
    资深
    -0.06
    大佬
    -0.06
    香港
    -0.06
    POSITIVE LOGITS
    �
    0.07
     uploads
    0.06
     classifications
    0.06
     hooks
    0.06
    -books
    0.06
     SOCKET
    0.06
     dispenser
    0.06
     wor
    0.06
     angles
    0.06
     hunted
    0.06
    Act Density 0.048%

    No Known Activations