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

    Neuronpedia

    INDEX
    Explanations

    offering alternatives or different topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    собенно
    0.77
     Особенно
    0.76
     iedere
    0.75
    随时
    0.75
    ക്കണം
    0.75
     особенно
    0.75
     particolarmente
    0.74
    poque
    0.72
     اضافه
    0.71
     rapidity
    0.70
    POSITIVE LOGITS
     alternative
    1.98
     alternatives
    1.83
     instead
    1.78
     other
    1.70
     Alternative
    1.68
     Instead
    1.61
     Alternatives
    1.58
    alternative
    1.54
     alternativa
    1.53
    Alternative
    1.51
    Act Density 1.521%

    No Known Activations