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

    Neuronpedia

    INDEX
    Explanations

    code and technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    XH
    -0.07
     Cottage
    -0.07
     allo
    -0.07
     Alexander
    -0.06
     abnormal
    -0.06
    .FLOAT
    -0.06
    ़ो
    -0.06
    ken
    -0.06
     reader
    -0.06
    沉
    -0.06
    POSITIVE LOGITS
     isEnabled
    0.07
    );;↵
    0.06
    _UFunction
    0.06
    0.06
    ,DB
    0.06
    =>{↵
    0.06
     ******************************************************************************/↵
    0.06
     schön
    0.06
    Ü
    0.06
    	ok
    0.06
    Act Density 0.000%

    No Known Activations