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

    Neuronpedia

    INDEX
    Explanations

    clear and clarity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     souvent
    0.85
     oftentimes
    0.77
     często
    0.76
    often
    0.76
     tzw
    0.75
     cosidd
    0.74
     нередко
    0.74
     traditionally
    0.73
     often
    0.73
     suelen
    0.73
    POSITIVE LOGITS
     clear
    1.62
     clearer
    1.62
    Clear
    1.54
     Clear
    1.50
    clear
    1.45
     clarity
    1.43
     comments
    1.42
    清晰
    1.37
     Clarity
    1.36
     clears
    1.36
    Act Density 0.216%

    No Known Activations