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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     που
    -0.09
    τε
    -0.08
     precisamente
    -0.08
    (action
    -0.08
    ，比如
    -0.08
    _CLASSES
    -0.08
    __(↵
    -0.07
    τερο
    -0.07
     Ralph
    -0.07
     tiled
    -0.07
    POSITIVE LOGITS
    Conclusion
    0.09
     Conclusion
    0.09
    stood
    0.08
     Rath
    0.08
     Logical
    0.08
    ibbean
    0.08
    <|call|>
    0.08
    achelorette
    0.08
     certeza
    0.08
     Tento
    0.08
    Act Density 0.109%

    No Known Activations