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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    installation
    -0.07
    riting
    -0.06
     рост
    -0.06
    рід
    -0.06
     Наг
    -0.06
    -force
    -0.06
     Sole
    -0.06
    Sidebar
    -0.06
    _Two
    -0.06
    速
    -0.06
    POSITIVE LOGITS
     lasc
    0.07
    aco
    0.07
     Clarence
    0.06
     alış
    0.06
    (mi
    0.06
     Paso
    0.06
     comport
    0.06
    lage
    0.06
     adversity
    0.06
     Village
    0.06
    Act Density 0.066%

    No Known Activations