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

    Neuronpedia

    INDEX
    Explanations

    applied to specific courses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     definitivo
    0.44
    ధాన
    0.43
    രാണ്
    0.41
    confirmed
    0.40
    確認
    0.39
     OpenAPI
    0.39
     तय
    0.39
    asz
    0.39
     آهي
    0.38
     расход
    0.38
    POSITIVE LOGITS
    সম্প
    0.40
    Studies
    0.38
     STUDIES
    0.38
     Having
    0.38
     Studies
    0.38
    Having
    0.37
     WHE
    0.37
    Elements
    0.37
    SPE
    0.37
    Eau
    0.37
    Act Density 0.000%

    No Known Activations