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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ://"
    -0.08
    -tw
    -0.07
     roulette
    -0.07
    ://'
    -0.07
    𝐺
    -0.07
     beh
    -0.07
     ?,
    -0.07
     namely
    -0.07
     Chi
    -0.07
    绿色
    -0.07
    POSITIVE LOGITS
    Disclosure
    0.07
    工夫
    0.07
    剡
    0.07
     administr
    0.06
    inel
    0.06
    arters
    0.06
    _CLASSES
    0.06
     Platforms
    0.06
    翊
    0.06
    _Window
    0.06
    Act Density 0.071%

    No Known Activations