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
     Phill
    -0.07
    єте
    -0.07
     одну
    -0.07
     saturation
    -0.06
     Sé
    -0.06
     Freder
    -0.06
     rabbit
    -0.06
     Encode
    -0.06
     trophy
    -0.06
     cows
    -0.06
    POSITIVE LOGITS
    пеки
    0.07
    undy
    0.06
    شد
    0.06
    >');
↵
    0.06
    (commands
    0.06
     );↵↵
    0.06
    Bạn
    0.06
     önüne
    0.06
     χρόνια
    0.06
    instein
    0.06
    Act Density 0.009%

    No Known Activations