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

    Neuronpedia

    INDEX
    Explanations

    quotations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    324
    -0.06
     Fan
    -0.06
    }`}
    -0.06
     adel
    -0.06
     Nẵng
    -0.06
     fueled
    -0.06
     fierc
    -0.05
    Even
    -0.05
     Familie
    -0.05
     discussion
    -0.05
    POSITIVE LOGITS
     Yin
    0.07
    atedRoute
    0.07
     виконання
    0.07
     بح
    0.07
     headaches
    0.07
    ViewChild
    0.06
    cellent
    0.06
    olland
    0.06
    patterns
    0.06
    -fl
    0.06
    Act Density 0.334%

    No Known Activations