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

    Neuronpedia

    INDEX
    Explanations

    phone communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    0.70
    initions
    0.60
     cuerpos
    0.59
    лии
    0.57
    డీపీ
    0.56
     빙
    0.56
    ice
    0.55
     Bing
    0.55
    শালী
    0.55
    лл
    0.54
    POSITIVE LOGITS
    电话
    0.88
     telefonu
    0.79
    電話
    0.79
     téléphonique
    0.77
     telephone
    0.75
    ST
    0.74
     phone
    0.71
    📞
    0.71
     hotline
    0.70
     téléphone
    0.70
    Act Density 0.071%

    No Known Activations