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

    Neuronpedia

    INDEX
    Explanations

    a wide variety of words somewhat relating to states of being, often related to health/body, as well as intensity-denoting words like "really".

    oai_token-act-pair · gemini-2.0-flash

    Random text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ########.
    -0.60
     QtCore
    -0.56
    HomeAsUpEnabled
    -0.53
     springfox
    -0.52
    PageRoute
    -0.49
    UPI
    -0.49
    AnimationsModule
    -0.49
    WindowEvent
    -0.48
    BagLayout
    -0.47
    PagerAdapter
    -0.47
    POSITIVE LOGITS
    <bos>
    1.74
     pleaſure
    0.63
     Jefus
    0.59
     itſelf
    0.58
     purpoſe
    0.57
     Efq
    0.57
     eût
    0.57
     kasarigan
    0.57
     Majefty
    0.56
     czeko
    0.56
    Act Density 1.672%

    No Known Activations