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

    Neuronpedia

    INDEX
    Explanations

    home

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     注意
    -0.07
     ноги
    -0.06
     erfol
    -0.06
    Fo
    -0.06
    ักร
    -0.06
    Easy
    -0.06
    Row
    -0.06
     잘
    -0.06
    盤
    -0.06
    луж
    -0.06
    POSITIVE LOGITS
    #↵
    0.07
     n
    0.07
     {...
    0.07
     observing
    0.06
    bear
    0.06
     `'
    0.06
    _beg
    0.06
     Grade
    0.06
     {:.
    0.06
     국제
    0.06
    Act Density 0.000%

    No Known Activations