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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sunday
    -0.07
    Months
    -0.07
     yani
    -0.06
     slipping
    -0.06
    pcion
    -0.06
    -K
    -0.06
     defamation
    -0.06
    ラス
    -0.06
    ани
    -0.06
    販売
    -0.06
    POSITIVE LOGITS
     защит
    0.07
    адки
    0.07
     лич
    0.06
     Without
    0.06
     """↵
    0.06
    onder
    0.06
     فوت
    0.06
     Patriots
    0.06
    VENT
    0.06
     obsess
    0.06
    Act Density 0.004%

    No Known Activations