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

    Neuronpedia

    INDEX
    Explanations

    is a, was created

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    0.33
    pura
    0.33
    椑
    0.32
     통해
    0.30
    逘
    0.29
    vra
    0.29
     jų
    0.29
     afresh
    0.29
     제공
    0.28
     ควร
    0.28
    POSITIVE LOGITS
     was
    0.40
     has
    0.37
    。『
    0.35
     were
    0.34
    。
    0.33
     belongs
    0.33
     is
    0.32
     can
    0.31
     had
    0.31
     the
    0.31
    Act Density 0.323%

    No Known Activations