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

    Neuronpedia

    INDEX
    Explanations

    list item markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    www
    0.46
    мпаваць
    0.36
     tutt
    0.35
     spectre
    0.34
     skall
    0.34
     jaun
    0.33
     രണ്ടു
    0.33
     situs
    0.32
     heresy
    0.32
     conjugacy
    0.32
    POSITIVE LOGITS
     🤔
    0.35
    িনি
    0.34
     Easier
    0.32
     близо
    0.32
    <0xC2>
    0.32
     Once
    0.32
     effortlessly
    0.32
    🍵
    0.32
     Around
    0.31
    ḗ
    0.31
    Act Density 0.116%

    No Known Activations