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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    了一遍
    -0.07
    @update
    -0.07
    -io
    -0.06
    Experience
    -0.06
    万台
    -0.06
    .room
    -0.06
    .sc
    -0.06
    感兴趣
    -0.06
    了一声
    -0.06
    zimmer
    -0.06
    POSITIVE LOGITS
    作物
    0.07
    Perhaps
    0.07
    واشن
    0.07
     bogus
    0.07
     вещ
    0.07
    อารม
    0.06
    谈谈
    0.06
    dot
    0.06
    werp
    0.06
     Packers
    0.06
    Act Density 0.012%

    No Known Activations