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

    Neuronpedia

    INDEX
    Explanations

    5

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utils
    -0.07
    mid
    -0.07
     colon
    -0.07
    deps
    -0.06
    weis
    -0.06
     marque
    -0.06
    анка
    -0.06
    좋
    -0.06
    _pa
    -0.06
    Smooth
    -0.06
    POSITIVE LOGITS
    ([↵
    0.06
     Ã
    0.06
    
    0.06
     створ
    0.06
     here
    0.06
     sponsor
    0.06
    ى
    0.06
    OTOS
    0.06
     lớ
    0.06
    &D
    0.06
    Act Density 0.000%

    No Known Activations