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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mes
    -0.07
     CONTROL
    -0.06
    Will
    -0.06
    CAR
    -0.06
    Admin
    -0.06
     Mar
    -0.06
    Workers
    -0.06
     materials
    -0.06
    支
    -0.06
    ajaran
    -0.06
    POSITIVE LOGITS
     babel
    0.07
     egregious
    0.06
    avored
    0.06
    ologne
    0.06
    ẫn
    0.06
    (userInfo
    0.06
     Howe
    0.06
     cô
    0.06
     incorporating
    0.06
     añ
    0.06
    Act Density 0.018%

    No Known Activations