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

    Neuronpedia

    INDEX
    Explanations

    the word "be"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.86
    AsUp
    -0.81
    EDEFAULT
    -0.79
     estekak
    -0.79
     Hadrian
    -0.79
    adays
    -0.77
    Rüyada
    -0.75
     câte
    -0.73
     obligado
    -0.73
     通販
    -0.72
    POSITIVE LOGITS
     &
    0.59
    anser
    0.58
     and
    0.57
     TO
    0.56
    rande
    0.53
     Klo
    0.52
     sec
    0.50
     Vander
    0.50
     term
    0.49
     AND
    0.49
    Act Density 0.055%

    No Known Activations