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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (element
    -0.08
     Huntington
    -0.07
    cont
    -0.07
    的部分
    -0.07
     TERMIN
    -0.06
    Principal
    -0.06
    _tv
    -0.06
     Elm
    -0.06
     DRAW
    -0.06
     Errors
    -0.06
    POSITIVE LOGITS
    抱歉
    0.07
     sotto
    0.07
    ↚
    0.06
    翈
    0.06
    DCALL
    0.06
    Sharper
    0.06
     dõi
    0.06
    วล
    0.06
     achieve
    0.06
    _RGBA
    0.06
    Act Density 0.002%

    No Known Activations