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

    Neuronpedia

    INDEX
    Explanations

    .appendChild

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arter
    -0.07
    净土
    -0.07
    但这
    -0.07
    lab
    -0.07
    dependency
    -0.06
    溜
    -0.06
    TF
    -0.06
    ning
    -0.06
    tip
    -0.06
    .responses
    -0.06
    POSITIVE LOGITS
     FactoryBot
    0.07
    �
    0.07
    Unix
    0.07
    LocalizedMessage
    0.07
    illiseconds
    0.07
     chois
    0.07
    キッチ
    0.07
    쩰
    0.06
    ]+$
    0.06
     Seiten
    0.06
    Act Density 0.001%

    No Known Activations