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

    Neuronpedia

    INDEX
    Explanations

    ** headlines **

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    公众号
    0.46
     séptimo
    0.41
     newsletter
    0.41
     podcast
    0.40
    ,*/}
    0.40
     coval
    0.38
    وزیشن
    0.38
     retour
    0.37
    ,@
    0.37
     આપે
    0.37
    POSITIVE LOGITS
    authors
    0.44
    ifty
    0.40
    Authors
    0.40
     христи
    0.40
    conscious
    0.40
     hurts
    0.39
    řen
    0.39
    leted
    0.39
    izes
    0.38
     எல்லாம்
    0.38
    Act Density 0.001%

    No Known Activations