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

    Neuronpedia

    INDEX
    Explanations

    Emails

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contrary
    -0.07
     müş
    -0.06
    mino
    -0.06
    Collection
    -0.06
    pton
    -0.06
     drew
    -0.06
     бра
    -0.06
    이비
    -0.06
     duration
    -0.06
     única
    -0.06
    POSITIVE LOGITS
    :::::::::::
    0.07
    	pr
    0.06
     Clar
    0.06
     |--
    0.06
    pattern
    0.06
    _rm
    0.06
    ائية
    0.06
    indice
    0.06
    	cin
    0.06
    );}↵
    0.06
    Act Density 0.012%

    No Known Activations