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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     believe
    -0.07
    Parcel
    -0.06
    اگ
    -0.06
     harek
    -0.06
    AutoresizingMask
    -0.06
    ptime
    -0.06
    langle
    -0.06
    _ajax
    -0.06
    خوان
    -0.06
     tř
    -0.06
    POSITIVE LOGITS
     union
    0.08
     math
    0.07
     ethical
    0.07
    ucks
    0.06
     Hindus
    0.06
     satellites
    0.06
     summ
    0.06
    एम
    0.06
    Commercial
    0.06
    육
    0.06
    Act Density 0.008%

    No Known Activations