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

    Neuronpedia

    INDEX
    Explanations

    important considerations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tip
    0.45
    关键字
    0.43
    supset
    0.41
    理由
    0.41
    Tip
    0.40
     Tipp
    0.39
    రువు
    0.39
     suggest
    0.39
     Hint
    0.39
    一部
    0.38
    POSITIVE LOGITS
     consideration
    1.00
    Consider
    1.00
     considered
    0.97
    consider
    0.94
     CONSIDER
    0.93
     consid
    0.92
     considerations
    0.92
     considér
    0.91
     considerar
    0.87
    考慮
    0.87
    Act Density 0.008%

    No Known Activations