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

    Neuronpedia

    INDEX
    Explanations

    structured text with lists and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    0.27
     sums
    0.27
    2
    0.24
    holds
    0.23
     at
    0.23
     op
    0.23
    LinkedIn
    0.23
     set
    0.23
     also
    0.22
    "]
    0.22
    POSITIVE LOGITS
     사람들이
    0.27
              
    0.26
    ↵
    0.25
     waarbij
    0.25
    скольку
    0.25
     Vì
    0.24
     Ideally
    0.24
     Factories
    0.24
     Polsce
    0.24
     這
    0.23
    Act Density 0.417%

    No Known Activations