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

    Neuronpedia

    INDEX
    Explanations

    DESC

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ěl
    -0.07
    間
    -0.07
     최고
    -0.07
    匹
    -0.07
    �试
    -0.07
    (nodes
    -0.07
    ايات
    -0.06
    ریب
    -0.06
    #.
    -0.06
    ुकस
    -0.06
    POSITIVE LOGITS
     DESC
    0.09
     bak
    0.07
    Finally
    0.06
     December
    0.06
    DESC
    0.06
     callback
    0.06
     Desc
    0.06
     medical
    0.06
     CN
    0.06
    -c
    0.06
    Act Density 0.001%

    No Known Activations