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

    Neuronpedia

    INDEX
    Explanations

    multilingual text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ט
    0.54
    tim
    0.48
    ้อ
    0.44
     المؤلف
    0.43
     रोडवेज
    0.43
    Tim
    0.42
    ing
    0.41
    Viele
    0.41
     thập
    0.40
    Directory
    0.40
    POSITIVE LOGITS
     assi
    0.50
    mba
    0.49
     eluted
    0.49
     grenades
    0.48
    ously
    0.48
     ого
    0.46
     OU
    0.46
    水の
    0.45
     коло
    0.45
     निकाय
    0.44
    Act Density 0.111%

    No Known Activations