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

    Neuronpedia

    INDEX
    Explanations

    proper nouns followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಾದರೂ
    0.29
     Amid
    0.26
     quelquefois
    0.24
    जिसे
    0.24
     থাকিলেও
    0.24
    Amid
    0.23
    幇
    0.23
     Hopefully
    0.23
     även
    0.23
     এটাও
    0.23
    POSITIVE LOGITS
     comes
    0.34
     gets
    0.33
     sits
    0.33
     goes
    0.32
     took
    0.32
     went
    0.31
     came
    0.30
     takes
    0.29
     loves
    0.29
     has
    0.28
    Act Density 0.059%

    No Known Activations