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

    Neuronpedia

    INDEX
    Explanations

    phrases involving directions or groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ⲱ
    0.62
    ϙ
    0.54
    𓏧
    0.54
    𝕨
    0.54
     রামগতি
    0.52
     niektórych
    0.52
    cotton
    0.51
    ക്കുകയും
    0.50
    ワ
    0.50
    ઊ
    0.49
    POSITIVE LOGITS
    ↵↵
    0.54
    ne
    0.47
    addressed
    0.46
    ment
    0.44
     spicy
    0.43
    ating
    0.42
     $
    0.42
    izing
    0.42
    ing
    0.41
     marketing
    0.41
    Act Density 0.001%

    No Known Activations