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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    城际
    -0.07
     буд
    -0.07
    偕
    -0.07
    牖
    -0.07
    بيب
    -0.07
    兕
    -0.07
    -chevron
    -0.07
    �
    -0.06
    科教
    -0.06
     decomposition
    -0.06
    POSITIVE LOGITS
     hal
    0.07
     material
    0.07
    尤其是在
    0.07
    为你
    0.06
    Hor
    0.06
    켇
    0.06
     accommodating
    0.06
     soll
    0.06
    fortunately
    0.06
    ifle
    0.06
    Act Density 0.001%

    No Known Activations