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

    Neuronpedia

    INDEX
    Explanations

    concluding statement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Heights
    -0.07
    Ր
    -0.07
    _aliases
    -0.07
    assert
    -0.07
     intimacy
    -0.07
    aut
    -0.06
    壯
    -0.06
    蒜
    -0.06
    凡
    -0.06
     isnt
    -0.06
    POSITIVE LOGITS
     chickens
    0.07
     próp
    0.07
    맸
    0.07
    скую
    0.07
     mock
    0.07
    -turn
    0.07
     cost
    0.07
    覚え
    0.07
     ticking
    0.06
    (Keys
    0.06
    Act Density 0.020%

    No Known Activations