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

    Neuronpedia

    INDEX
    Explanations

    indexes and analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     condos
    0.42
    imilar
    0.41
    fordern
    0.40
     churches
    0.39
    renched
    0.39
    ]._
    0.39
     እስ
    0.38
    我现在
    0.38
     valt
    0.37
     summits
    0.37
    POSITIVE LOGITS
    revise
    0.42
     måle
    0.42
     contradict
    0.42
     abolish
    0.42
    WithType
    0.41
     Supplemental
    0.41
     examine
    0.40
     analyze
    0.40
     revise
    0.39
    examine
    0.39
    Act Density 0.003%

    No Known Activations