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

    Neuronpedia

    INDEX
    Explanations

    sure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     文
    -0.07
     Anal
    -0.06
     attrib
    -0.06
    wendung
    -0.06
     ـ
    -0.06
    	center
    -0.06
     ngại
    -0.06
    접
    -0.06
    COD
    -0.06
    .pa
    -0.05
    POSITIVE LOGITS
    elijke
    0.08
    真是
    0.07
    」↵↵
    0.07
     vaguely
    0.06
    _execute
    0.06
     seedu
    0.06
     generate
    0.06
    обы
    0.06
    woods
    0.06
     парамет
    0.06
    Act Density 0.000%

    No Known Activations