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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pects
    -0.06
    fifo
    -0.06
    uelve
    -0.06
    Construct
    -0.06
    يدا
    -0.06
    koli
    -0.06
    DCF
    -0.06
    ledon
    -0.06
     cic
    -0.06
    スコ
    -0.06
    POSITIVE LOGITS
    /up
    0.07
     Working
    0.07
     borderline
    0.07
    应用
    0.07
     Exercises
    0.07
    .ax
    0.06
    //!↵
    0.06
    ('>
    0.06
     nz
    0.06
    (library
    0.06
    Act Density 0.067%

    No Known Activations