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

    Neuronpedia

    INDEX
    Explanations

    It

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    火爆
    -0.06
     некотор
    -0.06
    ользоват
    -0.06
    .people
    -0.06
    .dtp
    -0.06
    괭
    -0.06
    “He
    -0.06
    投注
    -0.06
     Controls
    -0.06
    เต
    -0.06
    POSITIVE LOGITS
    орт
    0.07
    急救
    0.07
     khối
    0.07
     stained
    0.07
    imir
    0.07
     Rag
    0.06
    איר
    0.06
    城市
    0.06
    кус
    0.06
     risen
    0.06
    Act Density 0.005%

    No Known Activations