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

    Neuronpedia

    INDEX
    Explanations

    Mam followed by other syllables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ([\
    0.56
    ([[
    0.45
    ッチ
    0.43
     yielding
    0.42
    ੍ਹਾਂ
    0.41
    ｍｍ
    0.40
    䳕
    0.39
    鑄
    0.38
    ]=\
    0.37
    ꯤ
    0.37
    POSITIVE LOGITS
     Mam
    0.44
     مام
    0.41
    Mam
    0.39
    ánsito
    0.39
     mam
    0.39
     DA
    0.38
     Goodbye
    0.37
     Cycle
    0.37
     Facts
    0.37
     Dolly
    0.37
    Act Density 0.001%

    No Known Activations