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

    Neuronpedia

    INDEX
    Explanations

    matched pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    daily
    0.39
     fast
    0.38
     daily
    0.38
    を買
    0.38
     ude
    0.38
     samego
    0.37
     protagonisti
    0.37
    Monty
    0.36
     új
    0.36
    に取り
    0.36
    POSITIVE LOGITS
     Kart
    0.39
     עס
    0.38
     обстанов
    0.38
     Verfahren
    0.37
     اقتصاد
    0.37
     `"
    0.37
    PROC
    0.36
    </tfoot>
    0.36
     Analytical
    0.36
    ﻰ
    0.36
    Act Density 0.000%

    No Known Activations