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

    Neuronpedia

    INDEX
    Explanations

    **

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MF
    -0.07
     Bra
    -0.07
    urrenc
    -0.07
    Century
    -0.07
    ֆ
    -0.07
    Ga
    -0.07
     uf
    -0.06
    _BLUE
    -0.06
     surpr
    -0.06
    ще
    -0.06
    POSITIVE LOGITS
     joining
    0.07
    توقيع
    0.07
    .squareup
    0.07
     توفير
    0.07
     voor
    0.07
    .'/
    0.07
    /includes
    0.07
    _my
    0.07
     kết
    0.07
     organising
    0.07
    Act Density 0.011%

    No Known Activations