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

    Neuronpedia

    INDEX
    Explanations

    human

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    矿
    -0.08
     سلامت
    -0.08
     مشکل
    -0.07
    _Product
    -0.07
     bs
    -0.07
    discord
    -0.07
     Collider
    -0.07
    قیق
    -0.07
    .Fixed
    -0.07
    泳
    -0.06
    POSITIVE LOGITS
    Hope
    0.07
     Breast
    0.06
     radi
    0.06
     Aff
    0.06
     beside
    0.06
     ordinarily
    0.06
    urpose
    0.06
    etermination
    0.06
    Construction
    0.06
    trak
    0.06
    Act Density 0.009%

    No Known Activations