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

    Neuronpedia

    INDEX
    Explanations

     the word "things" (sometimes near other words)

    oai_token-act-pair · gemini-2.0-flash

    things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myſelf
    -1.55
     Efq
    -1.52
     Majefty
    -1.47
     Houſe
    -1.41
     themſelves
    -1.40
     Jefus
    -1.39
     purpoſe
    -1.36
     himſelf
    -1.33
     itſelf
    -1.33
     houſe
    -1.32
    POSITIVE LOGITS
     تضيفلها
    0.68
     kasarigan
    0.68
    openSession
    0.66
    ImageContext
    0.64
    ьаж
    0.64
    XmlAccessType
    0.61
    Чыганаклар
    0.61
    __(
    0.61
    daq
    0.60
         
    0.59
    Act Density 2.980%

    No Known Activations