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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     barrier
    -0.07
    .getElementsByTagName
    -0.06
     hạng
    -0.06
    .ticket
    -0.06
     Mexicans
    -0.06
     tussen
    -0.06
    ział
    -0.06
    行动
    -0.06
    tiler
    -0.06
     акти
    -0.06
    POSITIVE LOGITS
     pioneers
    0.07
     troubling
    0.07
     WTO
    0.07
    =query
    0.06
    lead
    0.06
     BDSM
    0.06
     preocup
    0.06
     Conan
    0.06
     Wise
    0.06
    ardu
    0.06
    Act Density 0.001%

    No Known Activations