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

    Neuronpedia

    INDEX
    Explanations

    states, suggests, argues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     connaissez
    0.44
     glances
    0.39
    Includes
    0.38
    に基づいて
    0.38
    Expressions
    0.38
     божомолдор
    0.38
    تبط
    0.37
     பற்றிய
    0.37
    Signs
    0.37
     vistazo
    0.37
    POSITIVE LOGITS
     stated
    1.25
     stating
    1.18
     states
    1.03
     assert
    0.96
    stated
    0.96
     afferma
    0.95
     asserts
    0.95
     says
    0.94
     menyatakan
    0.94
     indicate
    0.91
    Act Density 0.192%

    No Known Activations