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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Albany
    -0.07
     fiberglass
    -0.07
    literal
    -0.07
    Seq
    -0.06
     Desk
    -0.06
    似乎
    -0.06
     denied
    -0.06
    =A
    -0.06
    pression
    -0.06
    alla
    -0.06
    POSITIVE LOGITS
     stagn
    0.07
     commencement
    0.07
     mãe
    0.07
    RAW
    0.07
    bsolute
    0.06
    Lt
    0.06
     boş
    0.06
     yerleştir
    0.06
    沖
    0.06
    ीं
    0.06
    Act Density 0.045%

    No Known Activations