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

    Neuronpedia

    INDEX
    Explanations

    still debated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inev
    1.06
     inevitable
    1.06
     inevitably
    1.00
     spurred
    0.83
     inroads
    0.82
     inescap
    0.81
     instigated
    0.81
     undertaken
    0.78
     spearheaded
    0.77
     قریب
    0.77
    POSITIVE LOGITS
     predmet
    0.84
    debate
    0.84
     debated
    0.82
     disputes
    0.79
     oggetto
    0.77
     डिस्कशन
    0.75
     tartış
    0.74
     произведение
    0.73
     dispute
    0.73
     debating
    0.73
    Act Density 0.088%

    No Known Activations