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

    Neuronpedia

    INDEX
    Explanations

    code delimiters and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    abhäng
    0.42
    mektedir
    0.40
     小学
    0.40
     لوبې
    0.39
    imers
    0.39
    ḵ
    0.39
    amboo
    0.38
    ellige
    0.38
    ochial
    0.38
     уеннары
    0.38
    POSITIVE LOGITS
    0.48
    <0xC2>
    0.40
    0.39
     जोकि
    0.39
       
    0.37
    <0xE3>
    0.35
     it
    0.35
      
    0.35
     fost
    0.35
     each
    0.34
    Act Density 0.037%

    No Known Activations