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

    Neuronpedia

    INDEX
    Explanations

    dataframe code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     decorrer
    -0.09
     lese
    -0.09
     immobilier
    -0.09
     प्रिय
    -0.08
    “I
    -0.08
     diversión
    -0.08
     proverbial
    -0.08
    “T
    -0.08
     tardes
    -0.08
    әр
    -0.08
    POSITIVE LOGITS
     Presented
    0.09
     Fragment
    0.08
    _fragment
    0.08
     fragment
    0.08
     format
    0.08
    riott
    0.08
    Fragment
    0.07
     Typically
    0.07
    _reporting
    0.07
     Often
    0.07
    Act Density 0.005%

    No Known Activations