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

    Neuronpedia

    INDEX
    Explanations

    poets and hymns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    accumulate
    -0.07
    /services
    -0.06
    LOC
    -0.06
    .accessToken
    -0.06
    .picture
    -0.06
     homosex
    -0.06
     unregister
    -0.06
    show
    -0.06
     лес
    -0.06
     flame
    -0.06
    POSITIVE LOGITS
    """↵↵
    0.07
     �
    0.07
    许多
    0.07
    这
    0.06
     tremendous
    0.06
    這
    0.06
    }))↵↵
    0.06
     �
    0.06
     olan
    0.06
     교수
    0.06
    Act Density 0.010%

    No Known Activations