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

    Neuronpedia

    INDEX
    Explanations

    B

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ArgumentException
    -0.07
    ⚠
    -0.07
    antically
    -0.07
    扫一
    -0.07
    女星
    -0.06
     Instance
    -0.06
    /resources
    -0.06
     suspense
    -0.06
    Ⲁ
    -0.06
     atmospheric
    -0.06
    POSITIVE LOGITS
     fullname
    0.07
     frontal
    0.07
    "profile
    0.07
    老头
    0.07
     unicorn
    0.07
    렀
    0.06
     hr
    0.06
    _episodes
    0.06
    رز
    0.06
    Tes
    0.06
    Act Density 0.001%

    No Known Activations