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

    Neuronpedia

    INDEX
    Explanations

    Wishes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disdain
    -0.07
     liqu
    -0.07
    -Mart
    -0.06
     Но
    -0.06
    ители
    -0.06
    /cache
    -0.06
    '+
    -0.06
    _slider
    -0.06
     sırada
    -0.06
    려고
    -0.06
    POSITIVE LOGITS
    (group
    0.08
     eyeb
    0.07
     grouped
    0.06
     إ
    0.06
    すぎ
    0.06
    request
    0.06
    _Resource
    0.06
     onwards
    0.06
     PSD
    0.06
     Frequently
    0.06
    Act Density 0.046%

    No Known Activations