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

    Neuronpedia

    INDEX
    Explanations

    was created or trained

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     habían
    0.52
     había
    0.41
     তথাপি
    0.40
     çalış
    0.39
     revers
    0.38
     neural
    0.38
    ixir
    0.38
     minhas
    0.37
     was
    0.37
    ⓗ
    0.37
    POSITIVE LOGITS
     Recently
    0.69
     bisher
    0.68
     recentemente
    0.68
    Recently
    0.67
    recently
    0.66
     récemment
    0.64
     autrefois
    0.63
     recently
    0.62
     recientemente
    0.61
     historically
    0.61
    Act Density 0.013%

    No Known Activations