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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    prime
    -0.07
    IVER
    -0.07
    staw
    -0.06
    oty
    -0.06
    eti
    -0.06
     Boise
    -0.06
    وجود
    -0.06
     noreferrer
    -0.06
    "time
    -0.06
    02
    -0.06
    POSITIVE LOGITS
    不足
    0.06
     السعود
    0.06
     mixins
    0.06
    enticate
    0.06
    国の
    0.06
     خدمت
    0.06
    athlete
    0.06
     흐
    0.06
    功能
    0.06
     пак
    0.06
    Act Density 0.075%

    No Known Activations