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

    Neuronpedia

    INDEX
    Explanations

    "as we know it" ending

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    投身
    -0.07
    Jon
    -0.07
    匙
    -0.07
    二胎
    -0.07
     sexes
    -0.07
     speeding
    -0.07
     Turk
    -0.07
    lapping
    -0.07
    (fd
    -0.07
     collaborations
    -0.07
    POSITIVE LOGITS
    /mit
    0.07
    rawid
    0.07
    :↵↵↵↵↵↵
    0.07
    选股
    0.06
    此处
    0.06
     understands
    0.06
     defines
    0.06
     대
    0.06
    "][
    0.06
     wordt
    0.06
    Act Density 0.013%

    No Known Activations