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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shelters
    -0.07
    开水
    -0.07
    -American
    -0.07
     אתם
    -0.07
     flushed
    -0.07
    avanaugh
    -0.06
    驾校
    -0.06
    ضعف
    -0.06
    滆
    -0.06
    システ
    -0.06
    POSITIVE LOGITS
     //~
    0.07
    0.07
     Interest
    0.07
     pis
    0.07
    sto
    0.07
    …”
    0.07
    ốn
    0.07
     min
    0.06
     Travis
    0.06
    توجه
    0.06
    Act Density 0.214%

    No Known Activations