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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     approximately
    -0.07
     Russo
    -0.06
    QUI
    -0.06
     XCT
    -0.06
     Sammy
    -0.06
     Jesse
    -0.06
    姆
    -0.06
     Vendor
    -0.06
    арам
    -0.06
    ूस
    -0.06
    POSITIVE LOGITS
    &(
    0.07
    _mr
    0.07
    ERSION
    0.06
    ηση
    0.06
     الح
    0.06
    (sel
    0.06
     JOB
    0.06
     рав
    0.06
    olkien
    0.06
    ){}↵
    0.06
    Act Density 0.013%

    No Known Activations