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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рин
    -0.07
     Watch
    -0.07
    _IRQHandler
    -0.06
     aprove
    -0.06
    鲜
    -0.06
    抗
    -0.06
    档
    -0.06
    Accessor
    -0.06
    rbrakk
    -0.06
     سود
    -0.06
    POSITIVE LOGITS
     "
    0.10
     “
    0.09
    “
    0.07
    ，“
    0.07
    ！↵
    0.06
    ,“
    0.06
     crackers
    0.06
    Dist
    0.06
    textAlign
    0.06
    =this
    0.06
    Act Density 0.001%

    No Known Activations