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

    Neuronpedia

    INDEX
    Explanations

    Pornography websites

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    本报记者
    -0.09
    iji
    -0.07
    あれ
    -0.07
    纪录
    -0.07
    _Show
    -0.07
    🔽
    -0.07
     işlemleri
    -0.07
    该剧
    -0.07
    すべて
    -0.07
    Spoiler
    -0.07
    POSITIVE LOGITS
    柱
    0.07
     initiating
    0.07
     evasion
    0.07
    尖
    0.06
    awner
    0.06
    etection
    0.06
     clearance
    0.06
    letion
    0.06
    astery
    0.06
    Trade
    0.06
    Act Density 0.002%

    No Known Activations