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

    Neuronpedia

    INDEX
    Explanations

    media

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drafting
    -0.06
     데이터
    -0.06
     Від
    -0.06
     Anaheim
    -0.06
     datasource
    -0.06
     парамет
    -0.06
    夫
    -0.06
     풀
    -0.06
    listener
    -0.06
     Sent
    -0.05
    POSITIVE LOGITS
    没
    0.07
    _bp
    0.07
     stakes
    0.06
     Begins
    0.06
    _ABS
    0.06
    挺
    0.06
    _tF
    0.06
     projev
    0.06
     ков
    0.06
    avar
    0.06
    Act Density 0.055%

    No Known Activations