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

    Neuronpedia

    INDEX
    Explanations

    vowels in code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    落实
    -0.08
    诇
    -0.07
     cuz
    -0.07
     encaps
    -0.06
     оказ
    -0.06
     Cinder
    -0.06
    헅
    -0.06
     cancelled
    -0.06
    ibern
    -0.06
     dollar
    -0.06
    POSITIVE LOGITS
    やはり
    0.08
     bees
    0.07
    党和
    0.07
    rike
    0.07
    된
    0.07
    пром
    0.07
    &(
    0.07
    $text
    0.07
     addAction
    0.07
    trieve
    0.07
    Act Density 0.010%

    No Known Activations