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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ’s
    -0.07
     cards
    -0.07
     familiar
    -0.06
     dân
    -0.06
    尽
    -0.06
     Halloween
    -0.06
     animal
    -0.06
     Rabbit
    -0.06
    Calculate
    -0.06
     حتى
    -0.06
    POSITIVE LOGITS
     me
    0.08
     you
    0.08
     YOU
    0.07
    .spinner
    0.07
     us
    0.07
    .Gen
    0.07
    ().'
    0.06
    (Index
    0.06
     XCTAssertTrue
    0.06
    .Ag
    0.06
    Act Density 0.085%

    No Known Activations