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

    Neuronpedia

    INDEX
    Explanations

    pronoun followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    可以在
    0.32
     BPA
    0.31
     Barge
    0.30
    adhar
    0.30
     יכול
    0.29
     Zip
    0.28
     Bisa
    0.28
     Deputy
    0.27
     Directorate
    0.26
     flutter
    0.26
    POSITIVE LOGITS
    ochastic
    0.33
    obbly
    0.32
     intersecting
    0.32
     sugi
    0.32
    ListItemIcon
    0.31
    لول
    0.31
     numerosos
    0.30
     histologic
    0.30
     berkualitas
    0.30
    ERTY
    0.29
    Act Density 0.004%

    No Known Activations