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

    Neuronpedia

    INDEX
    Explanations

    and continue / still

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     complètement
    0.42
    âu
    0.42
     ce
    0.39
    🌼
    0.38
     évent
    0.38
     dém
    0.36
     tadi
    0.36
    Otherwise
    0.36
     yell
    0.36
    üü
    0.35
    POSITIVE LOGITS
     continues
    0.71
    continues
    0.63
     continue
    0.61
     ভবিষ্য
    0.60
     продолжает
    0.59
     आजही
    0.56
    continue
    0.54
     BEEN
    0.52
     CONTINUE
    0.51
     продовжу
    0.51
    Act Density 0.012%

    No Known Activations