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
     dictates
    -0.06
     finanzi
    -0.06
     todd
    -0.06
    asta
    -0.06
     occur
    -0.06
     inadequate
    -0.06
    floor
    -0.06
     місцев
    -0.06
    Products
    -0.06
     bölg
    -0.06
    POSITIVE LOGITS
    βι
    0.07
     تج
    0.07
    $form
    0.07
     pem
    0.07
    ough
    0.07
    	path
    0.07
    (req
    0.07
     Cache
    0.06
    文件
    0.06
    弱
    0.06
    Act Density 0.000%

    No Known Activations