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

    Neuronpedia

    INDEX
    Explanations

    list items separated by &

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bảo
    0.54
     bảo
    0.47
    ორი
    0.47
     обеспечение
    0.47
    abung
    0.46
     eliminado
    0.46
     derrot
    0.46
    ุ
    0.44
    colFirst
    0.43
    azol
    0.43
    POSITIVE LOGITS
     subtitle
    0.53
    Subtitle
    0.46
     Aussage
    0.44
    t
    0.44
     Scrooge
    0.44
     طبي
    0.43
    Conversation
    0.43
     rectify
    0.42
    Word
    0.41
    Stainless
    0.41
    Act Density 0.001%

    No Known Activations