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

    Neuronpedia

    INDEX
    Explanations

    idea

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chữa
    -0.07
    ีเอ
    -0.07
    sometimes
    -0.07
     Malaysian
    -0.06
     de
    -0.06
    NOT
    -0.06
    Dog
    -0.06
    곡
    -0.06
     Elves
    -0.06
     ROOT
    -0.06
    POSITIVE LOGITS
     {!
    0.07
    用的
    0.06
     пр
    0.06
    (`<
    0.06
    erry
    0.06
     )}↵
    0.06
    =in
    0.06
    ливості
    0.06
    ált
    0.06
    ･
    0.06
    Act Density 0.194%

    No Known Activations