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

    Neuronpedia

    INDEX
    Explanations

    memory addresses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     зат
    -0.07
    릿
    -0.07
     Mush
    -0.07
     органі
    -0.06
     explo
    -0.06
     �
    -0.06
    _buckets
    -0.06
     دوست
    -0.06
     getApp
    -0.06
     th�
    -0.06
    POSITIVE LOGITS
    ................
    0.08
     screwed
    0.06
    .GetById
    0.06
     Wild
    0.06
     VOC
    0.06
    ................................
    0.06
    -low
    0.06
    .......
    0.06
    "]=
    0.06
     &#
    0.06
    Act Density 0.010%

    No Known Activations