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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     olduğu
    -0.07
     Hopkins
    -0.06
    look
    -0.06
     　　　　　　　　　　　　　　　　
    -0.06
     Rectangle
    -0.06
     dys
    -0.06
    .way
    -0.06
     improvement
    -0.06
    してい
    -0.06
     Dob
    -0.06
    POSITIVE LOGITS
    _("
    0.07
    utilus
    0.07
    .ensure
    0.06
     Rever
    0.06
    embourg
    0.06
    Liked
    0.06
    Of
    0.06
    aga
    0.06
     INTERRU
    0.06
     cooker
    0.06
    Act Density 0.090%

    No Known Activations