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

    Neuronpedia

    INDEX
    Explanations

    possessives and contractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     }^{[
    0.52
     cấu
    0.51
     karenge
    0.51
    色
    0.50
     esport
    0.50
     hội
    0.50
     tiềm
    0.50
     màu
    0.50
     aktiv
    0.49
     corrosive
    0.49
    POSITIVE LOGITS
    an
    0.58
    lk
    0.54
    ar
    0.52
    ob
    0.50
    yk
    0.49
    itäten
    0.48
     অন্তত
    0.48
    asis
    0.47
    en
    0.47
    na
    0.46
    Act Density 0.001%

    No Known Activations