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

    Neuronpedia

    INDEX
    Explanations

    constant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     이제
    -0.08
     Setup
    -0.08
    不僅
    -0.07
     And
    -0.07
     explanations
    -0.07
     Jacket
    -0.07
     commonplace
    -0.07
    stellung
    -0.07
    QUEUE
    -0.07
    更新
    -0.07
    POSITIVE LOGITS
     Bru
    0.07
    猝
    0.07
     авиа
    0.07
    苾
    0.07
    |`↵
    0.07
    ��取
    0.06
     milfs
    0.06
     kids
    0.06
    פסטיבל
    0.06
    🚄
    0.06
    Act Density 0.009%

    No Known Activations