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

    Neuronpedia

    INDEX
    Explanations

    sending something out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ༣
    0.29
     newsletters
    0.28
     söyle
    0.28
    webs
    0.27
    客户
    0.27
    咵
    0.27
     filtre
    0.26
    კ
    0.26
     sklep
    0.26
     filtros
    0.26
    POSITIVE LOGITS
     వచ్చి
    0.26
     මෙ
    0.26
     Assuming
    0.25
     Sum
    0.25
     Declined
    0.25
    ંમે
    0.25
     declining
    0.25
     于
    0.24
     tgt
    0.24
     sil
    0.24
    Act Density 0.001%

    No Known Activations