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

    Neuronpedia

    INDEX
    Explanations

    code and file formats

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [H
    -0.07
    Mu
    -0.07
    VERRIDE
    -0.06
     internship
    -0.06
     Tran
    -0.06
    -word
    -0.06
    ridden
    -0.06
    [G
    -0.06
    <N
    -0.06
     chuyện
    -0.06
    POSITIVE LOGITS
     aşağı
    0.07
     nucleus
    0.07
     SOUND
    0.06
     Đối
    0.06
    'e
    0.06
     vyd
    0.06
     kindergarten
    0.06
     unus
    0.06
    alcon
    0.06
     obou
    0.06
    Act Density 0.006%

    No Known Activations