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

    Neuronpedia

    INDEX
    Explanations

    Historical context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	best
    -0.06
     successor
    -0.06
     واحدة
    -0.06
    $url
    -0.06
    ]interface
    -0.06
     riding
    -0.06
    reeting
    -0.06
     fired
    -0.06
     diverse
    -0.06
    Boolean
    -0.06
    POSITIVE LOGITS
     republiky
    0.07
     stockholm
    0.07
    ίων
    0.07
     nouvelle
    0.07
    bildung
    0.07
    rike
    0.07
    bern
    0.06
    <button
    0.06
    시는
    0.06
    _C
    0.06
    Act Density 0.079%

    No Known Activations