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

    Neuronpedia

    INDEX
    Explanations

    negative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ins
    -0.07
    肯
    -0.07
    '%(
    -0.06
     inflated
    -0.06
    Green
    -0.06
    frames
    -0.06
    随处可见
    -0.06
     pan
    -0.06
    rooms
    -0.06
    cap
    -0.06
    POSITIVE LOGITS
    incible
    0.07
     CJ
    0.07
    工程施工
    0.07
    工程技术
    0.07
     Baxter
    0.07
     друг
    0.07
     Rune
    0.07
     athe
    0.06
     Люб
    0.06
    ˵
    0.06
    Act Density 0.080%

    No Known Activations