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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    student
    -0.07
     Bayer
    -0.07
     працівників
    -0.06
     nedir
    -0.06
    ówn
    -0.06
    تیب
    -0.06
     CONTRACT
    -0.06
    Mon
    -0.06
     LAN
    -0.06
    Weapon
    -0.06
    POSITIVE LOGITS
    0
    0.07
    합
    0.07
     regardless
    0.06
    anker
    0.06
    št
    0.06
    MING
    0.06
    输出
    0.06
    anks
    0.06
    BUF
    0.06
     Watkins
    0.06
    Act Density 0.014%

    No Known Activations