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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Retrieve
    -0.08
     padre
    -0.07
     resemblance
    -0.07
     reports
    -0.07
     Video
    -0.07
    _instance
    -0.07
     pleasure
    -0.07
     vacations
    -0.06
    program
    -0.06
    seconds
    -0.06
    POSITIVE LOGITS
     Tight
    0.07
    maktadır
    0.07
     nokt
    0.07
     tortured
    0.06
     дет
    0.06
    	exports
    0.06
    中に
    0.06
     چیز
    0.06
    -----------
↵
    0.06
     pint
    0.06
    Act Density 0.033%

    No Known Activations