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

    Neuronpedia

    INDEX
    Explanations

    Technical files and documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imax
    -0.07
     Thy
    -0.06
     Mor
    -0.06
    _Rect
    -0.06
     Simple
    -0.06
    AJ
    -0.06
     Kam
    -0.06
     congestion
    -0.06
     Del
    -0.06
     mktime
    -0.06
    POSITIVE LOGITS
    386
    0.07
    covers
    0.06
    643
    0.06
     bied
    0.06
    ỳ
    0.06
    дия
    0.06
     لكل
    0.06
    reten
    0.06
    anya
    0.06
    PE
    0.06
    Act Density 0.018%

    No Known Activations