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

    Neuronpedia

    INDEX
    Explanations

    logic puzzles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    almost
    -0.07
    _regex
    -0.07
     unordered
    -0.06
     olduğu
    -0.06
     zbyt
    -0.06
     initialised
    -0.06
     pancreatic
    -0.06
    Let
    -0.06
    edi
    -0.06
     Feder
    -0.06
    POSITIVE LOGITS
     ש
    0.07
    onents
    0.06
    +'/
    0.06
    âm
    0.06
    乙
    0.06
     Precision
    0.06
    >();
↵
    0.06
    ={↵
    0.06
    اقع
    0.06
    .'</
    0.06
    Act Density 0.010%

    No Known Activations