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

    Neuronpedia

    INDEX
    Explanations

    scraped/code disclaimers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    YNAMIC
    -0.07
    ect
    -0.06
     ilet
    -0.06
     Par
    -0.06
    _Tab
    -0.06
    čet
    -0.06
    ORM
    -0.06
    .document
    -0.06
    orm
    -0.06
    plets
    -0.06
    POSITIVE LOGITS
    .Marker
    0.07
     MAG
    0.07
     تأ
    0.06
     रख
    0.06
    [args
    0.06
     seinen
    0.06
     profoundly
    0.06
     Manuals
    0.06
    сим
    0.06
    すぐ
    0.06
    Act Density 0.085%

    No Known Activations