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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Legacy
    -0.07
     PSG
    -0.07
    elon
    -0.07
     pong
    -0.06
    _BP
    -0.06
    UX
    -0.06
     confines
    -0.06
    actical
    -0.06
    arus
    -0.06
     Portal
    -0.06
    POSITIVE LOGITS
    建议
    0.07
     symptom
    0.07
    	sign
    0.06
    。この
    0.06
     nhiên
    0.06
    (run
    0.06
    .writeln
    0.06
    .bpm
    0.06
    ymce
    0.06
    戒
    0.06
    Act Density 0.004%

    No Known Activations