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

    Neuronpedia

    INDEX
    Explanations

    meta tags and configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অপর্ণ
    0.29
    odoris
    0.28
    tenance
    0.27
     शुरुआ
    0.26
    榊
    0.26
    lerimiz
    0.25
    EnglishMarks
    0.25
    rrrr
    0.25
    <unused438>
    0.24
    كام
    0.24
    POSITIVE LOGITS
     [
    0.29
     文
    0.26
     hai
    0.26
     テ
    0.26
     hou
    0.26
     nel
    0.26
     mili
    0.26
    ю
    0.25
     неф
    0.25
     możliwość
    0.25
    Act Density 0.035%

    No Known Activations