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

    Neuronpedia

    INDEX
    Explanations

    chunk splitting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )^{*}\
    0.41
     ماشینونو
    0.40
     تشدد
    0.40
    ܒ
    0.39
     क्रिप्टोकरेंसी
    0.39
     shortcomings
    0.38
     Clustering
    0.38
     conflit
    0.38
     impotence
    0.38
    筝
    0.38
    POSITIVE LOGITS
    Separator
    0.43
     তীর
    0.41
    ремен
    0.41
    SEPARATOR
    0.40
    extensive
    0.37
     institution
    0.37
     લગ
    0.36
    Tik
    0.36
    हीत
    0.36
     अभिव
    0.35
    Act Density 0.001%

    No Known Activations