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

    Neuronpedia

    INDEX
    Explanations

    accuracy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tooltip
    -0.06
    plist
    -0.06
     ایشان
    -0.06
     kterých
    -0.06
     mktime
    -0.06
     wh
    -0.06
     норм
    -0.06
     parece
    -0.06
     necessities
    -0.06
     creepy
    -0.06
    POSITIVE LOGITS
     CENT
    0.08
    /upload
    0.07
    utive
    0.07
     bergen
    0.07
    otional
    0.06
    Compra
    0.06
    rored
    0.06
    ermo
    0.06
     разви
    0.06
    icago
    0.06
    Act Density 0.055%

    No Known Activations