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

    Neuronpedia

    INDEX
    Explanations

    academic texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     longevity
    -0.06
    کن
    -0.06
    @c
    -0.06
    ourses
    -0.06
    [Double
    -0.06
    sigma
    -0.06
    $con
    -0.06
     reachable
    -0.06
    코
    -0.06
     adverse
    -0.06
    POSITIVE LOGITS
     erkek
    0.07
    _DEAD
    0.07
     Yuk
    0.07
    isel
    0.06
     karak
    0.06
     "::
    0.06
    ::|
    0.06
     wirk
    0.06
    ५
    0.06
     srp
    0.06
    Act Density 0.067%

    No Known Activations