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

    Neuronpedia

    INDEX
    Explanations

    hello

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     max
    -0.08
    _frequency
    -0.07
    ופ
    -0.07
     dấu
    -0.07
    Ὃ
    -0.07
    ǔ
    -0.07
    夫
    -0.07
     khổ
    -0.07
    ��
    -0.06
     qp
    -0.06
    POSITIVE LOGITS
     brunette
    0.07
    얄
    0.07
    benh
    0.07
    收纳
    0.07
    앳
    0.07
    '>
↵
    0.06
    甜甜
    0.06
     tatsäch
    0.06
    略微
    0.06
    皙
    0.06
    Act Density 0.013%

    No Known Activations