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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    کور
    -0.07
    67
    -0.07
    /Form
    -0.07
    WRAPPER
    -0.07
     stationed
    -0.06
    كور
    -0.06
    90
    -0.06
    _CAN
    -0.06
    -Star
    -0.06
    dll
    -0.06
    POSITIVE LOGITS
     přem
    0.07
     Minh
    0.07
     пере
    0.07
     Priority
    0.07
     replica
    0.06
     transformation
    0.06
     dönüş
    0.06
    -me
    0.06
    irection
    0.06
    	ans
    0.06
    Act Density 0.017%

    No Known Activations