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

    Neuronpedia

    INDEX
    Explanations

    lists/categories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ers
    -0.08
     الثالث
    -0.07
    Ze
    -0.07
    Com
    -0.07
    438
    -0.07
     جم
    -0.07
     theft
    -0.07
    子
    -0.06
     withdrawals
    -0.06
    Jam
    -0.06
    POSITIVE LOGITS
    _mac
    0.07
    afety
    0.06
    .Yes
    0.06
    ntp
    0.06
    ...(
    0.06
    sync
    0.06
    айт
    0.06
     Greenwood
    0.06
     pošk
    0.06
    iday
    0.06
    Act Density 0.010%

    No Known Activations