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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ination
    -0.07
    дами
    -0.06
    parable
    -0.06
     �
    -0.06
    dir
    -0.06
    Threads
    -0.06
     rozum
    -0.06
    раг
    -0.06
     coaching
    -0.06
    ня
    -0.06
    POSITIVE LOGITS
    。今
    0.07
     grands
    0.07
    _sur
    0.06
    _SMS
    0.06
     Reminder
    0.06
    υνα
    0.06
    .Len
    0.06
    :N
    0.06
    [OF
    0.06
     *((
    0.06
    Act Density 0.002%

    No Known Activations