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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jedno
    -0.07
     záv
    -0.07
     لك
    -0.07
    'en
    -0.07
    .nextLine
    -0.07
     یون
    -0.07
    _ctr
    -0.06
     üzerindeki
    -0.06
    DDS
    -0.06
    Automatic
    -0.06
    POSITIVE LOGITS
    们
    0.06
    -strip
    0.06
    一年
    0.06
    ?↵
    0.06
    artial
    0.06
    通过
    0.06
    "",↵
    0.06
    를
    0.06
     Psalm
    0.06
    	finally
    0.06
    Act Density 0.000%

    No Known Activations