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

    Neuronpedia

    INDEX
    Explanations

    Math/scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pert
    -0.07
     viên
    -0.07
     Cv
    -0.07
     goog
    -0.07
    拳头
    -0.07
     FTC
    -0.06
    少量
    -0.06
     cres
    -0.06
     fatt
    -0.06
     IW
    -0.06
    POSITIVE LOGITS
    enade
    0.07
    accumulate
    0.07
    �
    0.06
    house
    0.06
     tłum
    0.06
    Obviously
    0.06
    urbed
    0.06
    ultan
    0.06
    run
    0.06
    okus
    0.06
    Act Density 0.018%

    No Known Activations