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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "I" alongside auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    Future actions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.75
    ########.
    -0.74
    Kanpo
    -0.61
    AutoScaleMode
    -0.57
    Приятного
    -0.55
    SharedDtor
    -0.52
    ]}>
    -0.52
     adipis
    -0.50
    aujourd
    -0.50
    KommentareTeilen
    -0.49
    POSITIVE LOGITS
    RectangleBorder
    0.54
    StoreMessageInfo
    0.54
     pysty
    0.49
    omock
    0.46
    الإنجليزية
    0.45
     ře
    0.45
     check
    0.45
     stick
    0.45
    tières
    0.45
     geslacht
    0.44
    Act Density 1.674%

    No Known Activations