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

    Neuronpedia

    INDEX
    Explanations

    source code loops and indexing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Glory
    -0.08
     discourse
    -0.08
    contest
    -0.08
     enjoyment
    -0.07
    illance
    -0.07
    WHEN
    -0.07
    reté
    -0.07
    Enjoy
    -0.07
     tribute
    -0.07
    ్రీ
    -0.07
    POSITIVE LOGITS
     تو
    0.08
    阴
    0.07
     এসব
    0.07
    Threads
    0.07
    _unknown
    0.07
     rhyth
    0.07
     واس
    0.07
     JObject
    0.07
     تخ
    0.07
     Lar
    0.07
    Act Density 0.003%

    No Known Activations