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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _alpha
    -0.07
    内部
    -0.07
     fibr
    -0.06
    ูน
    -0.06
     fixtures
    -0.06
     portrays
    -0.06
    ۶
    -0.06
     Sends
    -0.06
     reviewers
    -0.06
    ládá
    -0.06
    POSITIVE LOGITS
    τζ
    0.07
    	contentPane
    0.06
    ста
    0.06
    encv
    0.06
     gard
    0.06
    manda
    0.06
    -opt
    0.06
    gent
    0.06
    -le
    0.06
    	Point
    0.06
    Act Density 0.000%

    No Known Activations