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

    Neuronpedia

    INDEX
    Explanations

    ard/forward

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     olives
    -0.08
     doctrines
    -0.08
     doctrine
    -0.08
    ério
    -0.08
     Doctrine
    -0.08
     leak
    -0.08
    пе
    -0.08
    经
    -0.07
    训
    -0.07
     الزيت
    -0.07
    POSITIVE LOGITS
     anticipation
    0.11
     eagerly
    0.11
     excitement
    0.10
    期待
    0.10
     מראש
    0.09
    楽し
    0.09
     المقبلة
    0.09
     आगामी
    0.09
     freuen
    0.09
     القادمة
    0.09
    Act Density 0.033%

    No Known Activations