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
    ﷲ
    -0.07
     Split
    -0.07
    以习近平
    -0.07
    	u
    -0.07
    تعا
    -0.07
    ﭫ
    -0.07
    Uluslararası
    -0.07
     Diagram
    -0.07
    'l
    -0.06
     vrou
    -0.06
    POSITIVE LOGITS
    efficient
    0.07
    ائح
    0.07
    �
    0.07
    ✱
    0.07
     stereotype
    0.06
    这个名字
    0.06
     safe
    0.06
    ≈
    0.06
     collegiate
    0.06
    .Payload
    0.06
    Act Density 0.002%

    No Known Activations