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

    Neuronpedia

    INDEX
    Explanations

    .org or .com domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ون
    0.54
    ку
    0.46
    ம்
    0.45
    ين
    0.43
    ي
    0.43
    י
    0.43
    ח
    0.43
    ాన్ని
    0.42
    ק
    0.42
     HAVE
    0.40
    POSITIVE LOGITS
    0.63
     a
    0.37
     {
    0.36
     this
    0.36
    <0x0D>
    0.35
    是
    0.34
     to
    0.34
     is
    0.34
     <
    0.34
     an
    0.33
    Act Density 5.287%

    No Known Activations