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

    Neuronpedia

    INDEX
    Explanations

    different categories or specific items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     этой
    0.40
     цієї
    0.38
     Renaissance
    0.37
     цього
    0.37
     дося
    0.37
    同样的
    0.37
    기와
    0.37
     হয়ে
    0.36
    으면
    0.36
     добавля
    0.36
    POSITIVE LOGITS
     vagin
    0.45
     maternal
    0.44
    凋
    0.43
     khuôn
    0.43
    不安
    0.42
     embarazo
    0.42
     prist
    0.42
     centro
    0.42
    jj
    0.42
     simpl
    0.41
    Act Density 0.009%

    No Known Activations