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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    国立
    -0.08
     renowned
    -0.07
     threat
    -0.07
    xfd
    -0.07
     opinión
    -0.07
    enefit
    -0.07
     shipment
    -0.07
    -tech
    -0.07
     Danish
    -0.07
     Coming
    -0.07
    POSITIVE LOGITS
    ♬
    0.08
    ...(
    0.08
    咖
    0.07
     synerg
    0.07
    _sleep
    0.07
    fully
    0.07
    잖아요
    0.07
    솜
    0.07
    鸡
    0.07
    (getResources
    0.07
    Act Density 0.076%

    No Known Activations