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

    Neuronpedia

    INDEX
    Explanations

    say "length or width"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     قلت
    -0.09
    Bills
    -0.08
     bottled
    -0.08
    уел
    -0.07
    ukut
    -0.07
    ukar
    -0.07
     قالت
    -0.07
     forklift
    -0.07
     olaraq
    -0.07
    ็ต
    -0.07
    POSITIVE LOGITS
     length
    0.36
     width
    0.34
    长度
    0.33
    length
    0.32
    Length
    0.32
     Length
    0.31
    _length
    0.31
    width
    0.29
    -length
    0.29
     Width
    0.29
    Act Density 0.133%

    No Known Activations