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

    Neuronpedia

    INDEX
    Explanations

    if...or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     flavoured
    0.49
     flavored
    0.48
     flavoring
    0.48
     unsold
    0.46
     waning
    0.44
    లిన
    0.44
     discoloration
    0.44
     saturation
    0.43
     paperwork
    0.42
     conducted
    0.42
    POSITIVE LOGITS
    יר
    0.52
    گ
    0.52
    يش
    0.49
    مد
    0.48
    ندی
    0.48
    ما
    0.48
    দি
    0.47
    یا
    0.46
    दि
    0.46
     combatt
    0.46
    Act Density 0.000%

    No Known Activations