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

    Neuronpedia

    INDEX
    Explanations

    start of document fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Category
    0.45
     Category
    0.45
     categorie
    0.43
    Categoria
    0.42
     category
    0.42
    idal
    0.41
    enu
    0.40
    мся
    0.40
     elementName
    0.40
    อายุ
    0.40
    POSITIVE LOGITS
     START
    0.47
     externally
    0.46
     commences
    0.44
     starts
    0.43
     aband
    0.42
     internally
    0.42
     commence
    0.40
    Starts
    0.40
    START
    0.39
     impeach
    0.39
    Act Density 0.007%

    No Known Activations