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

    Neuronpedia

    INDEX
    Explanations

    a variety of common words and phrases, and doesn't seem to have a consistent pattern

    oai_token-act-pair · gemini-2.0-flash

    Book excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.69
    AnimationsModule
    -0.64
    <bos>
    -0.63
    webElementXpaths
    -0.61
    AndEndTag
    -0.57
     ©️
    -0.54
    jména
    -0.53
    offsetof
    -0.52
     CreateTagHelper
    -0.52
     ...]
    -0.52
    POSITIVE LOGITS
    ruptedException
    0.76
     OBITUARY
    0.61
    igshid
    0.56
     Sicher
    0.52
     sclero
    0.51
     Zweig
    0.50
    InSection
    0.49
     Webcam
    0.49
    ̍t
    0.48
    Rohy
    0.48
    Act Density 2.751%

    No Known Activations