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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.58
     ultimi
    -0.55
     rêves
    -0.54
     cucchiaio
    -0.53
     últimos
    -0.53
     respeito
    -0.50
     contribué
    -0.50
    nacht
    -0.48
     notwithstanding
    -0.48
     garantis
    -0.47
    POSITIVE LOGITS
     they
    1.09
     it
    1.05
     this
    0.90
     such
    0.79
     these
    0.77
     doing
    0.72
    这样做
    0.71
     their
    0.71
    awtextra
    0.71
     itinéraires
    0.69
    Act Density 0.004%

    No Known Activations