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

    Neuronpedia

    INDEX
    Explanations

    W

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    01
    -0.07
     creek
    -0.06
     warm
    -0.06
    tid
    -0.06
    fd
    -0.06
    ानव
    -0.06
     سپ
    -0.06
     temple
    -0.06
    (Pos
    -0.06
    surf
    -0.06
    POSITIVE LOGITS
    英
    0.07
    .exception
    0.07
    .Course
    0.06
     Celebration
    0.06
     genders
    0.06
     çek
    0.06
     thiểu
    0.06
    &S
    0.06
     Accuracy
    0.06
    岳
    0.06
    Act Density 0.000%

    No Known Activations