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

    Neuronpedia

    INDEX
    Explanations

    line

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itin
    -0.08
     clearly
    -0.07
    �
    -0.07
     wearable
    -0.07
     Nature
    -0.07
     civilizations
    -0.07
     civilization
    -0.07
     willingly
    -0.07
     Muslim
    -0.07
     писал
    -0.07
    POSITIVE LOGITS
     CURLOPT
    0.08
     команды
    0.08
     deutschland
    0.08
     tabindex
    0.08
     Cancellation
    0.08
     rer
    0.08
     попасть
    0.08
    ANGO
    0.08
     Instead
    0.08
     Verkehr
    0.08
    Act Density 0.000%

    No Known Activations