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

    Neuronpedia

    INDEX
    Explanations

    recall or remember

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ן
    2.38
    ii
    2.27
    j
    2.14
    ના
    2.09
    i
    2.05
    ui
    2.03
    ни
    1.96
    ní
    1.91
    ০
    1.91
    ד
    1.91
    POSITIVE LOGITS
     fondly
    2.55
    ্টেন
    1.91
     goo
    1.89
    сив
    1.80
    শনাল
    1.71
    үкт
    1.67
     preamble
    1.65
     rudimentary
    1.63
    ્સ
    1.62
     braz
    1.60
    Act Density 0.044%

    No Known Activations