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

    Neuronpedia

    INDEX
    Explanations

    verbs ending in -ing with following noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     has
    0.72
    র
    0.70
    ito
    0.68
     praised
    0.68
    at
    0.68
     is
    0.67
    re
    0.67
    de
    0.67
     ដើម្បី
    0.67
     seguenti
    0.65
    POSITIVE LOGITS
     encoders
    0.53
    वण
    0.50
     bialgebras
    0.49
    력이
    0.49
    턴
    0.48
    들이
    0.47
    ?")
    0.47
     workflows
    0.46
     axles
    0.46
    ळख
    0.46
    Act Density 0.244%

    No Known Activations