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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the phrase "I'm sure"

    oai_token-act-pair · gemini-2.0-flash

    sure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sén
    -0.47
    TM
    -0.45
     scaricare
    -0.45
     nozze
    -0.44
     ambassade
    -0.41
     '.$
    -0.41
    {
    -0.41
     alcuna
    -0.41
     cinematogra
    -0.40
     diſt
    -0.40
    POSITIVE LOGITS
    perhaps
    0.81
     disambiguazione
    0.80
     perhaps
    0.80
    awtextra
    0.79
     maybe
    0.79
    anskje
    0.77
     perchance
    0.75
    maybe
    0.75
    Vielleicht
    0.75
    PyExc
    0.73
    Act Density 0.825%

    No Known Activations