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

    Neuronpedia

    INDEX
    Explanations

    tend to exhibit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hopefully
    0.49
     very
    0.46
     hopefully
    0.45
     très
    0.45
     VERY
    0.45
     muy
    0.44
     occasionally
    0.44
     optionally
    0.43
    Ideally
    0.42
    Hopefully
    0.42
    POSITIVE LOGITS
     tended
    0.77
     tend
    0.75
     outperformed
    0.68
     tende
    0.68
     outperform
    0.66
     tienden
    0.64
    tend
    0.63
     outperforms
    0.61
     fared
    0.60
     tiende
    0.59
    Act Density 0.029%

    No Known Activations