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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    аті
    -0.07
    erde
    -0.07
     Array
    -0.06
     rhetorical
    -0.06
    	defer
    -0.06
    จะเป
    -0.06
     tvoří
    -0.06
     nhưng
    -0.06
    odoxy
    -0.06
     hoặc
    -0.06
    POSITIVE LOGITS
     Poke
    0.06
    基本
    0.06
    кап
    0.06
     "))↵
    0.06
    _deleted
    0.06
    碼
    0.06
    -param
    0.06
     educated
    0.06
    quoi
    0.06
    sı
    0.06
    Act Density 0.003%

    No Known Activations