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

    Neuronpedia

    INDEX
    Explanations

    guilty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iks
    -0.07
    ira
    -0.06
    ASCADE
    -0.06
    ifes
    -0.06
    aley
    -0.06
    ynet
    -0.06
    _field
    -0.06
    hosts
    -0.06
    olicies
    -0.06
    OLUMNS
    -0.06
    POSITIVE LOGITS
    --){↵
    0.07
     XCTAssertTrue
    0.07
     ||
↵
    0.07
     guilty
    0.07
     underst
    0.07
     admitting
    0.06
    classNames
    0.06
    ++++
    0.06
    刚才
    0.06
    (CType
    0.06
    Act Density 0.004%

    No Known Activations