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

    Neuronpedia

    INDEX
    Explanations

    Technical/Academic Writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enson
    -0.07
    сот
    -0.07
    cart
    -0.07
    ernational
    -0.07
     сказав
    -0.06
    displayName
    -0.06
     Cathy
    -0.06
    etí
    -0.06
    "Oh
    -0.06
     flash
    -0.06
    POSITIVE LOGITS
     modes
    0.07
     verifying
    0.07
     adversaries
    0.06
     agreements
    0.06
     اساسی
    0.06
    REDENTIAL
    0.06
     คาส
    0.06
    }(
    0.06
     locking
    0.06
    こう
    0.06
    Act Density 0.000%

    No Known Activations