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

    Neuronpedia

    INDEX
    Explanations

    loyal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ě
    -0.07
    dataGridView
    -0.07
    /=
    -0.07
    etically
    -0.07
    -billion
    -0.07
    reck
    -0.06
     Beds
    -0.06
     Это
    -0.06
     pct
    -0.06
    (act
    -0.06
    POSITIVE LOGITS
     loyalty
    0.08
    医生
    0.07
     diligent
    0.07
    產品
    0.07
    _mac
    0.07
    锆
    0.07
     loyal
    0.07
    薷
    0.06
    AndFeel
    0.06
     resil
    0.06
    Act Density 0.009%

    No Known Activations