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

    Neuronpedia

    INDEX
    Explanations

    jury

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    不同意
    -0.07
     paw
    -0.07
     phé
    -0.06
    mium
    -0.06
    yards
    -0.06
    .",
    -0.06
     cities
    -0.06
    商铺
    -0.06
    ator
    -0.06
     Signs
    -0.06
    POSITIVE LOGITS
    缭
    0.08
     Plot
    0.07
     الحاج
    0.07
     demasi
    0.07
     trance
    0.07
     onPress
    0.07
     influ
    0.07
    掮
    0.07
    רוב
    0.07
    全日制
    0.07
    Act Density 0.059%

    No Known Activations