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

    Neuronpedia

    INDEX
    Explanations

    Ongoing investigations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    奖励
    -0.07
    _ENCOD
    -0.06
    _font
    -0.06
    樂
    -0.06
     Jerome
    -0.06
     delays
    -0.06
    Stan
    -0.06
    מוס
    -0.06
     Sms
    -0.06
    Couldn
    -0.06
    POSITIVE LOGITS
    暴涨
    0.08
    各行各
    0.07
    iliation
    0.07
    最为
    0.07
    确诊病例
    0.07
     takeaway
    0.07
    ltr
    0.07
    家电
    0.07
    URES
    0.07
    [right
    0.07
    Act Density 0.123%

    No Known Activations