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

    Neuronpedia

    INDEX
    Explanations

    sharing among multiple users

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rows
    -0.08
     Macros
    -0.07
    머
    -0.07
    .Uri
    -0.07
     perpetual
    -0.07
    _opcode
    -0.07
    	cursor
    -0.06
     Char
    -0.06
    Outline
    -0.06
     Printing
    -0.06
    POSITIVE LOGITS
    ={{↵
    0.07
    ونت
    0.07
    ,'
    0.07
     mom
    0.07
    ış
    0.06
     obligatory
    0.06
     sö
    0.06
     savage
    0.06
     sprint
    0.06
    获取
    0.06
    Act Density 0.052%

    No Known Activations