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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    txn
    -0.08
    ttu
    -0.08
    rv
    -0.07
    daj
    -0.07
    της
    -0.07
     प्रतिक्रिया
    -0.07
     quartet
    -0.07
     כ
    -0.07
    для
    -0.07
    Cleanup
    -0.07
    POSITIVE LOGITS
     contrairement
    0.09
     Cyl
    0.09
    ್ವಹ
    0.08
     règles
    0.08
    OSS
    0.07
     previstas
    0.07
     lubrication
    0.07
     cylinders
    0.07
     dents
    0.07
     previsto
    0.07
    Act Density 0.000%

    No Known Activations