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

    Neuronpedia

    INDEX
    Explanations

    valid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    쥔
    -0.07
    اط
    -0.07
    scatter
    -0.06
    Ѓ
    -0.06
    _TE
    -0.06
     bonding
    -0.06
    관계
    -0.06
    �件
    -0.06
     Conn
    -0.06
    ouri
    -0.06
    POSITIVE LOGITS
    国人
    0.09
    	make
    0.07
     bacon
    0.07
    国际化
    0.07
    Palindrome
    0.07
     Hazel
    0.07
    信徒
    0.07
    (reordered
    0.07
    太阳能
    0.07
     mutually
    0.07
    Act Density 0.024%

    No Known Activations