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

    Neuronpedia

    INDEX
    Explanations

    Martini

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ON
    -0.07
    юк
    -0.06
     piles
    -0.06
     USAGE
    -0.06
     Gold
    -0.06
    ’:
    -0.06
     Sunrise
    -0.06
     století
    -0.06
    �江
    -0.06
     fame
    -0.06
    POSITIVE LOGITS
    .textContent
    0.07
    ург
    0.06
     viewController
    0.06
     hend
    0.06
    .assertIsInstance
    0.06
    typed
    0.06
    รณ
    0.06
    DIR
    0.06
     preservation
    0.05
    تي
    0.05
    Act Density 0.002%

    No Known Activations