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

    Neuronpedia

    INDEX
    Explanations

    Political articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     J
    -0.06
     funds
    -0.06
     grieving
    -0.06
     ≠
    -0.06
     米
    -0.06
    burg
    -0.06
    칭
    -0.06
     rủi
    -0.06
    شود
    -0.06
    病
    -0.06
    POSITIVE LOGITS
     contestants
    0.08
    攻撃
    0.07
    taş
    0.07
     LOL
    0.07
     hüc
    0.06
     etraf
    0.06
    _FC
    0.06
     BOOLEAN
    0.06
    したら
    0.06
    LLLL
    0.06
    Act Density 0.019%

    No Known Activations