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

    Neuronpedia

    INDEX
    Explanations

    explaining english options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    quatre
    0.46
    ریب
    0.43
    rifft
    0.43
    霁
    0.42
    ürnberg
    0.42
     četiri
    0.41
     무슨
    0.41
    ẳn
    0.41
     senhores
    0.40
     আসছে
    0.40
    POSITIVE LOGITS
    الح
    0.57
    ಅ
    0.52
    I
    0.51
    ఈ
    0.51
     Allergy
    0.50
    s
    0.50
    એ
    0.50
    Your
    0.49
    ی
    0.49
     this
    0.49
    Act Density 0.000%

    No Known Activations