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

    Neuronpedia

    INDEX
    Explanations

    website descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rello
    -0.07
    され
    -0.07
     Quando
    -0.07
    黑夜
    -0.07
     computers
    -0.07
    측
    -0.06
     Le
    -0.06
     MMM
    -0.06
    으면
    -0.06
    였
    -0.06
    POSITIVE LOGITS
    甑
    0.06
     bury
    0.06
    中国古代
    0.06
    EFR
    0.06
    醒了
    0.06
    븀
    0.06
     Ember
    0.06
    ód
    0.06
    文中
    0.06
     outr
    0.06
    Act Density 0.047%

    No Known Activations