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

    Neuronpedia

    INDEX
    Explanations

    less in number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     establishments
    0.45
     everytime
    0.45
     ins
    0.43
     opcode
    0.43
    Owned
    0.43
     milik
    0.43
    ossians
    0.43
     idempotent
    0.43
    Businesses
    0.42
     ideals
    0.41
    POSITIVE LOGITS
    ♀
    0.49
     виды
    0.46
     दो
    0.46
     wooded
    0.45
    quad
    0.44
     две
    0.43
     Nomenclature
    0.43
     первая
    0.42
     экологи
    0.42
     ”,
    0.42
    Act Density 0.024%

    No Known Activations