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

    Neuronpedia

    INDEX
    Explanations

    Notion software, app, database, offline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Therefore
    0.40
     Autism
    0.40
    immediately
    0.40
     शुभारंभ
    0.39
    Tales
    0.38
    Even
    0.38
    enture
    0.38
     ৭৮
    0.38
     seek
    0.38
     Websites
    0.38
    POSITIVE LOGITS
     drogas
    0.48
     केश
    0.45
     summed
    0.44
     llegando
    0.44
    ptica
    0.43
     représentant
    0.42
     başta
    0.42
     filhos
    0.42
     primos
    0.41
     ficando
    0.41
    Act Density 0.006%

    No Known Activations