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

    Neuronpedia

    INDEX
    Explanations

    text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    佯
    -0.07
     aeros
    -0.07
    �
    -0.06
    绿水青山
    -0.06
    各异
    -0.06
    ,"\
    -0.06
    PreferredSize
    -0.06
     RJ
    -0.06
    削弱
    -0.06
    不会有
    -0.06
    POSITIVE LOGITS
     scalar
    0.08
    	Check
    0.07
    >manual
    0.07
    _d
    0.07
    神器
    0.07
     sender
    0.07
    	var
    0.06
     Grinder
    0.06
    推出的
    0.06
     Sau
    0.06
    Act Density 0.346%

    No Known Activations