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

    Neuronpedia

    INDEX
    Explanations

    inappropriate requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    585
    -0.08
     bipartisan
    -0.08
     seismic
    -0.08
     KING
    -0.08
     Eureka
    -0.08
    �
    -0.08
    책
    -0.08
     Blackboard
    -0.08
    “一带一路
    -0.08
    대표
    -0.08
    POSITIVE LOGITS
     humiliation
    0.12
     humili
    0.12
    CMC
    0.08
     quedar
    0.08
    ADV
    0.08
     sexuales
    0.08
    idepress
    0.08
     oppressive
    0.08
    0.08
    ホテル
    0.08
    Act Density 0.235%
    No Known Activations