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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -li
    -0.06
     Attendance
    -0.06
    аліз
    -0.06
     forgetting
    -0.06
    Line
    -0.06
     residences
    -0.06
     victory
    -0.06
     Prostit
    -0.06
    =r
    -0.06
    ‌رس
    -0.06
    POSITIVE LOGITS
    (tasks
    0.07
    oon
    0.06
    <void
    0.06
     fon
    0.06
     erotici
    0.06
     Autof
    0.06
    (position
    0.06
    XYZ
    0.06
     ener
    0.06
    fred
    0.06
    Act Density 0.106%

    No Known Activations