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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     loop
    -0.08
    holm
    -0.07
    raction
    -0.07
    raid
    -0.07
     dru
    -0.07
    ankan
    -0.06
     preocup
    -0.06
    塑
    -0.06
    bij
    -0.06
    á
    -0.06
    POSITIVE LOGITS
    _marshaled
    0.07
    🚐
    0.07
    (bounds
    0.07
    正常使用
    0.07
     orange
    0.07
    '[
    0.07
     Daw
    0.07
    _PWR
    0.07
    _msgs
    0.07
    海淀
    0.07
    Act Density 0.046%

    No Known Activations