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

    Neuronpedia

    INDEX
    Explanations

    groups

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    剧本
    -0.08
     PPC
    -0.07
    这样的
    -0.07
    這種
    -0.07
     spokeswoman
    -0.07
     Ves
    -0.07
    href
    -0.07
     medicinal
    -0.07
    捨
    -0.07
     VERY
    -0.07
    POSITIVE LOGITS
    createElement
    0.08
    娆
    0.07
    channels
    0.07
    נס
    0.07
     stranger
    0.07
     oldest
    0.06
     команд
    0.06
     exiting
    0.06
    🇰
    0.06
    _parents
    0.06
    Act Density 0.010%

    No Known Activations