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

    Neuronpedia

    INDEX
    Explanations

    every word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Extend
    0.45
     Raise
    0.40
    われた
    0.39
     Ante
    0.39
    Carr
    0.39
    Paw
    0.38
     Completed
    0.37
    క్షి
    0.37
    われます
    0.36
    君
    0.36
    POSITIVE LOGITS
     reacciones
    0.43
     mango
    0.42
     hummus
    0.41
     अच
    0.41
     necesariamente
    0.40
     llor
    0.39
     mannitol
    0.39
     duduk
    0.38
     впечат
    0.38
     сидя
    0.38
    Act Density 0.003%

    No Known Activations