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

    Neuronpedia

    INDEX
    Explanations

    to verb infinitive

    np_acts-logits-general · gemini-2.5-flash-lite

    if you were

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.35
    ?
    0.35
     are
    0.34
    ö
    0.33
     an
    0.32
    ud
    0.32
    ও
    0.31
    iku
    0.30
    ın
    0.30
    aw
    0.30
    POSITIVE LOGITS
     saddhim
    0.33
     expts
    0.29
     namani
    0.28
    你了
    0.28
    畚
    0.28
    щик
    0.27
    yatiti
    0.27
     ممال
    0.27
     editorials
    0.27
    ଚ
    0.27
    Act Density 0.893%

    No Known Activations