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

    Neuronpedia

    INDEX
    Explanations

    Sensors and detection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cheng
    -0.07
    Mensaje
    -0.07
    Hen
    -0.07
     everyone
    -0.07
     viewType
    -0.06
     Chemical
    -0.06
     accepting
    -0.06
     scooter
    -0.06
     مشاهدة
    -0.06
    Century
    -0.06
    POSITIVE LOGITS
    327
    0.07
    軽
    0.06
    546
    0.06
    #######↵
    0.06
     Manufacturer
    0.06
    UIT
    0.06
    缓
    0.06
    .S
    0.06
    619
    0.06
     XCTAssertEqual
    0.06
    Act Density 0.145%

    No Known Activations