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

    Neuronpedia

    INDEX
    Explanations

    random text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    אשר
    -0.08
    _excerpt
    -0.08
    )|(
    -0.08
    ."'
    -0.08
     Jas
    -0.08
    廉洁
    -0.07
    😿
    -0.07
     prise
    -0.07
    村党支部
    -0.07
    )+(
    -0.07
    POSITIVE LOGITS
    	UP
    0.08
    ℕ
    0.07
    pay
    0.07
     american
    0.07
     arm
    0.07
    西装
    0.07
     chocolate
    0.07
    	Close
    0.07
     stress
    0.06
     impact
    0.06
    Act Density 0.041%

    No Known Activations