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

    Neuronpedia

    INDEX
    Explanations

    predicting next word

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    重新
    -0.07
    证明
    -0.06
    ,test
    -0.06
    uers
    -0.06
     kraje
    -0.06
     Members
    -0.06
     praised
    -0.06
     �
    -0.06
     coh
    -0.06
    -м
    -0.06
    POSITIVE LOGITS
     spiral
    0.06
    Feedback
    0.06
    */,↵
    0.06
    _tail
    0.06
     */↵↵↵
    0.06
    ')]↵
    0.06
    Office
    0.06
    suspend
    0.06
    .openg
    0.06
    /releases
    0.06
    Act Density 0.004%

    No Known Activations