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

    Neuronpedia

    INDEX
    Explanations

    dose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iden
    -0.07
    >');↵
    -0.06
     Dong
    -0.06
     sept
    -0.06
     books
    -0.06
    ників
    -0.06
    FromDate
    -0.06
    _volume
    -0.06
    -training
    -0.06
    ился
    -0.06
    POSITIVE LOGITS
     حافظ
    0.07
    ycl
    0.07
     intrigued
    0.07
    -area
    0.06
    hazi
    0.06
     zas
    0.06
    wild
    0.06
    _lng
    0.06
    :y
    0.06
    _md
    0.06
    Act Density 0.013%

    No Known Activations