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

    Neuronpedia

    INDEX
    Explanations

    cells

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Constants
    -0.07
     porn
    -0.07
    .err
    -0.06
     جمع
    -0.06
    觀
    -0.06
     gel
    -0.06
     ApiResponse
    -0.06
     Bru
    -0.06
     хотя
    -0.06
     ResponseEntity
    -0.06
    POSITIVE LOGITS
    (fields
    0.07
    _Write
    0.06
    park
    0.06
    ้าของ
    0.06
    ';↵↵
    0.06
    ]-'
    0.06
     XCTAssertEqual
    0.06
    Supply
    0.06
    _split
    0.06
     РФ
    0.06
    Act Density 0.033%

    No Known Activations