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

    Neuronpedia

    INDEX
    Explanations

    如下

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Russ
    -0.07
    _m
    -0.06
    XmlElement
    -0.06
    ลอง
    -0.06
    =""
    -0.06
    '}}↵
    -0.06
    Lang
    -0.06
    Equipment
    -0.06
    环
    -0.06
    면
    -0.06
    POSITIVE LOGITS
    ControlEvents
    0.07
    šet
    0.06
     lasers
    0.06
    521
    0.06
    오
    0.06
    ammer
    0.06
     màu
    0.06
    prompt
    0.06
     Kick
    0.06
    /blue
    0.06
    Act Density 0.011%

    No Known Activations