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

    Neuronpedia

    INDEX
    Explanations

    semif

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     (()
    -0.07
    的一个
    -0.07
    enin
    -0.06
     名前
    -0.06
     orada
    -0.06
    珠
    -0.06
     Европ
    -0.06
    _partitions
    -0.06
    ович
    -0.06
     strtoupper
    -0.06
    POSITIVE LOGITS
     textbooks
    0.08
     aids
    0.06
    论
    0.06
    _Source
    0.06
    )::
    0.06
     Design
    0.06
     Bh
    0.06
    (chip
    0.06
    WI
    0.06
     Mud
    0.06
    Act Density 0.013%

    No Known Activations