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

    Neuronpedia

    INDEX
    Explanations

    translation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     прав
    -0.07
     sổ
    -0.06
    휑
    -0.06
    公务
    -0.06
    𫛭
    -0.06
    .Username
    -0.06
     yoğun
    -0.06
    𝇠
    -0.06
    鬣
    -0.06
    抬起
    -0.06
    POSITIVE LOGITS
    Choices
    0.08
    fraction
    0.07
    callbacks
    0.07
    cq
    0.07
    NEW
    0.07
    AGEMENT
    0.07
     sublime
    0.07
     dominates
    0.06
    organisms
    0.06
     motel
    0.06
    Act Density 0.012%

    No Known Activations