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

    Neuronpedia

    INDEX
    Explanations

    book

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _nums
    -0.07
     рах
    -0.06
    ζό
    -0.06
     щось
    -0.06
    璃
    -0.06
    ениях
    -0.06
    emax
    -0.06
    uits
    -0.06
     Riot
    -0.06
     سمت
    -0.06
    POSITIVE LOGITS
     finer
    0.07
     Book
    0.07
     Preparation
    0.06
    -ticket
    0.06
     cyn
    0.06
     settles
    0.06
    (adj
    0.06
     captured
    0.06
     household
    0.06
    _PM
    0.06
    Act Density 0.007%

    No Known Activations