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

    Neuronpedia

    INDEX
    Explanations

    st

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    entr
    -0.30
    ä¸ĭæ²ī
    -0.28
    çĭĢ
    -0.27
     gon
    -0.27
    NIC
    -0.27
    çĿĽ
    -0.26
    两æĿ¡
    -0.26
     spoiler
    -0.26
    åħĴ
    -0.25
    mw
    -0.25
    POSITIVE LOGITS
     >>
    0.27
    ort
    0.26
    itorio
    0.25
     holders
    0.25
    æŶä¸į
    0.25
    ityEngine
    0.24
     -
    0.24
    IT
    0.24
    æł·æľ¬
    0.24
    itant
    0.23
    Act Density 3.396%

    No Known Activations