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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mathematical
    -0.07
    ✐
    -0.07
    vec
    -0.07
     Icelandic
    -0.07
     spooky
    -0.07
     vão
    -0.07
    何も
    -0.07
     Solve
    -0.07
     string
    -0.06
    íg
    -0.06
    POSITIVE LOGITS
    唷
    0.07
    ('-',
    0.07
    给你们
    0.07
    嗪
    0.07
    living
    0.07
    CES
    0.07
     tur
    0.07
    重要讲话
    0.07
    واقع
    0.07
    瓣
    0.06
    Act Density 0.002%

    No Known Activations