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

    Neuronpedia

    INDEX
    Explanations

    Lesser

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ذكر
    -0.07
    composed
    -0.07
     meas
    -0.06
     activate
    -0.06
    烟
    -0.06
    .MenuItem
    -0.06
    radu
    -0.06
     kino
    -0.06
     말이
    -0.06
     redesign
    -0.06
    POSITIVE LOGITS
     upset
    0.07
     fittings
    0.07
     setType
    0.07
     suspense
    0.06
     Screens
    0.06
     Machinery
    0.06
     Луч
    0.06
    async
    0.06
    avourite
    0.06
    Cookies
    0.06
    Act Density 0.001%

    No Known Activations