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

    Neuronpedia

    INDEX
    Explanations

    be or to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ː
    -0.08
     Dich
    -0.08
     Seiten
    -0.07
    钪
    -0.07
    .div
    -0.07
     stockholm
    -0.07
    FullYear
    -0.07
    锃
    -0.07
    驾照
    -0.07
    ⧼
    -0.07
    POSITIVE LOGITS
     STE
    0.07
    _RT
    0.07
    壞
    0.07
    ovo
    0.07
     usb
    0.07
     tum
    0.07
     landlord
    0.06
    _angles
    0.06
    噪音
    0.06
    Triangle
    0.06
    Act Density 0.006%

    No Known Activations