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

    Neuronpedia

    INDEX
    Explanations

    user assistant message exchanges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     man's
    -0.09
    avista
    -0.09
     estaría
    -0.08
     이번
    -0.08
     plötzlich
    -0.08
     vox
    -0.08
    fails
    -0.08
     tərə
    -0.08
     tack
    -0.08
     girl's
    -0.07
    POSITIVE LOGITS
     documented
    0.11
    截至
    0.11
     documentation
    0.10
     cited
    0.10
    Text
    0.09
     text
    0.09
    According
    0.09
    官方
    0.09
    Documentation
    0.09
     citations
    0.08
    Act Density 0.131%

    No Known Activations