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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﻟ�
    -0.06
     tact
    -0.06
     Pou
    -0.06
    음을
    -0.06
    ocê
    -0.06
    恵
    -0.06
    ovie
    -0.06
    QQ
    -0.06
     花
    -0.06
     utiliza
    -0.06
    POSITIVE LOGITS
     Beste
    0.07
     trest
    0.06
    finalize
    0.06
    ая
    0.06
    еры
    0.06
    _tree
    0.06
    _NE
    0.06
    repid
    0.06
    Bounding
    0.06
     (↵
    0.06
    Act Density 0.080%

    No Known Activations