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

    Neuronpedia

    INDEX
    Explanations

    Rules and regulations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     эффектив
    -0.07
     nạn
    -0.07
     张
    -0.07
    来的
    -0.07
    ậy
    -0.07
    ってい
    -0.06
     꼭
    -0.06
     planets
    -0.06
     پیشنه
    -0.06
    622
    -0.06
    POSITIVE LOGITS
    Capt
    0.06
    _MAIN
    0.06
    Chunk
    0.06
    Duplicates
    0.06
     Vice
    0.06
    wiki
    0.06
    ingu
    0.06
     tomb
    0.05
    <IEnumerable
    0.05
    ladu
    0.05
    Act Density 0.100%

    No Known Activations