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

    Neuronpedia

    INDEX
    Explanations

    medical symptoms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _male
    -0.06
     Industries
    -0.06
    ordo
    -0.06
     نوشته
    -0.06
     inflicted
    -0.06
    Physics
    -0.06
    líž
    -0.06
     episode
    -0.06
    StdString
    -0.06
     состоит
    -0.06
    POSITIVE LOGITS
     Jug
    0.07
    を行
    0.06
    }'.
    0.06
     dafür
    0.06
    IEL
    0.06
    .NONE
    0.06
     Knee
    0.06
     %.
    0.06
    uellen
    0.06
    \<
    0.06
    Act Density 0.013%

    No Known Activations