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

    Neuronpedia

    INDEX
    Explanations

    the noun phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arXiv
    0.36
     równ
    0.36
     htmlFor
    0.33
     esche
    0.32
     ạ
    0.32
    laştır
    0.32
    畯
    0.32
    ँ
    0.31
    圣
    0.31
    िष्ट
    0.30
    POSITIVE LOGITS
     تعداد
    0.35
     equipments
    0.35
     availed
    0.35
     endearing
    0.34
     materialistic
    0.33
    concerned
    0.33
     concerned
    0.32
     evidences
    0.32
     aforesaid
    0.32
     hitherto
    0.32
    Act Density 0.015%

    No Known Activations