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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal strings

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intellectual
    0.73
     ninth
    0.72
     Bản
    0.71
     UR
    0.71
     quarter
    0.71
     Southern
    0.70
     लक्षात
    0.68
     spotlight
    0.68
    úr
    0.68
     URI
    0.67
    POSITIVE LOGITS
    age
    0.73
    7
    0.73
    sticks
    0.71
    дки
    0.67
     fizer
    0.67
    ణా
    0.66
    ដ្ឋ
    0.64
    delicious
    0.64
    ូ
    0.63
    <unused72>
    0.63
    Act Density 0.005%

    No Known Activations