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

    Neuronpedia

    INDEX
    Explanations

    English Composition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Официа
    0.51
    ørt
    0.50
    ཌ
    0.49
     Ağustos
    0.49
    jonen
    0.43
    ТЕ
    0.42
     Temmuz
    0.42
    ιου
    0.42
    潸
    0.42
     शुक्रिया
    0.42
    POSITIVE LOGITS
     mentoring
    0.41
     laboratory
    0.41
     mentor
    0.41
     mentored
    0.38
    )*
    0.37
     levels
    0.37
     workshops
    0.36
     seminars
    0.36
     research
    0.36
    |}{
    0.36
    Act Density 0.003%

    No Known Activations