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

    Neuronpedia

    INDEX
    Explanations

    greetings in multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     digs
    0.39
    硌
    0.38
    श्किल
    0.37
    買った
    0.37
    哪怕
    0.36
     relativement
    0.36
     μεγαλύτε
    0.36
     লোহার
    0.36
     possède
    0.36
     potencialmente
    0.36
    POSITIVE LOGITS
     greetings
    0.53
     н
    0.49
     🙏
    0.48
    申し上げ
    0.46
     الجميع
    0.46
     하겠습니다
    0.45
     감사합니다
    0.44
     Greetings
    0.44
     바랍니다
    0.44
     вашей
    0.43
    Act Density 0.050%

    No Known Activations