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

    Neuronpedia

    INDEX
    Explanations

    words related to ordering or sequencing of processes, sometimes with an element of causality

    oai_token-act-pair · gemini-2.0-flash

    instructions/procedure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     juſt
    -0.80
     purpoſe
    -0.79
     becauſe
    -0.76
     sauvages
    -0.74
     Abonnez
    -0.73
     reaſon
    -0.73
     privées
    -0.73
     humaines
    -0.73
     himſelf
    -0.73
     vectorielles
    -0.73
    POSITIVE LOGITS
     then
    0.94
     Then
    0.88
     THEN
    0.83
    Then
    0.81
    THEN
    0.75
     puis
    0.68
    ثم
    0.66
    then
    0.63
     ثم
    0.63
    Puis
    0.62
    Act Density 1.136%

    No Known Activations