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

    Neuronpedia

    INDEX
    Explanations

    code and data structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    executor
    -0.08
    袭击
    -0.07
    	plt
    -0.07
    あたり
    -0.07
    _TOOL
    -0.07
    乐队
    -0.07
     abusing
    -0.07
     airing
    -0.07
    ッシュ
    -0.07
    _sibling
    -0.07
    POSITIVE LOGITS
    ಊ
    0.07
    꼇
    0.07
    റ
    0.07
     kötü
    0.07
    分流
    0.06
    />.↵
    0.06
    //=
    0.06
     trebuie
    0.06
    뮨
    0.06
     :
↵
    0.06
    Act Density 0.001%

    No Known Activations