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

    Neuronpedia

    INDEX
    Explanations

    balancing concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ग
    0.54
     catalysts
    0.52
    ر
    0.49
    立法
    0.45
     koop
    0.45
    ठा
    0.45
    แพทย์
    0.43
    р
    0.43
     backgrounds
    0.43
    ospels
    0.43
    POSITIVE LOGITS
     -$
    0.52
     Samsung
    0.50
     Apply
    0.50
     Data
    0.50
     ₽
    0.49
     Secure
    0.49
     حتی
    0.48
     nuovo
    0.47
     좋아요
    0.47
     લગભગ
    0.47
    Act Density 0.004%

    No Known Activations