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

    Neuronpedia

    INDEX
    Explanations

    UTF

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xing
    -0.07
    utas
    -0.07
     proyectos
    -0.07
    항
    -0.06
    HR
    -0.06
    axon
    -0.06
    (props
    -0.06
     Brend
    -0.06
     squeeze
    -0.06
    /vnd
    -0.06
    POSITIVE LOGITS
     able
    0.07
    法师
    0.07
    _STENCIL
    0.07
    //!↵
    0.07
    !I
    0.07
    \[
    0.06
     occur
    0.06
    🐾
    0.06
    国内外
    0.06
     Initi
    0.06
    Act Density 0.001%

    No Known Activations