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

    Neuronpedia

    INDEX
    Explanations

    complexity, multilingual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    able
    0.52
    ABLE
    0.51
    piele
    0.48
    ably
    0.47
     करने
    0.47
     कर
    0.45
    izando
    0.44
     किया
    0.43
    ishing
    0.43
     करती
    0.42
    POSITIVE LOGITS
     observables
    0.47
     CCS
    0.46
     discrimination
    0.46
     extrapolation
    0.44
     determinants
    0.44
     deletion
    0.43
     gauges
    0.43
     Jensen
    0.43
     discontinuity
    0.43
     eigenvalues
    0.43
    Act Density 0.108%

    No Known Activations