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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     στους
    -0.06
    .Branch
    -0.06
    Ack
    -0.06
     gum
    -0.06
     ।↵
    -0.06
    ử
    -0.06
    Neither
    -0.06
     estos
    -0.06
     tentang
    -0.06
     hh
    -0.06
    POSITIVE LOGITS
    -events
    0.06
    lian
    0.06
    原
    0.06
     apparatus
    0.06
    (script
    0.06
     ally
    0.06
    ARGET
    0.06
     DIRECT
    0.06
     Differences
    0.06
    _context
    0.06
    Act Density 0.051%

    No Known Activations