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

    Neuronpedia

    INDEX
    Explanations

    exemplifies concepts with specific examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     preferably
    0.50
    的意思
    0.46
     either
    0.44
    preferably
    0.43
    Usually
    0.42
     Preferably
    0.40
    either
    0.38
     entweder
    0.38
    together
    0.38
    Either
    0.38
    POSITIVE LOGITS
     misalnya
    0.86
     mesela
    0.85
     उदाहरण
    0.84
     similarly
    0.83
     например
    0.83
     exemplo
    0.82
     beispielsweise
    0.82
     exemplifies
    0.82
     bijvoorbeeld
    0.82
     famously
    0.81
    Act Density 0.048%

    No Known Activations