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

    Neuronpedia

    INDEX
    Explanations

    start of an address

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اً
    1.08
    カ
    1.03
    اقة
    1.02
    OLI
    1.00
    ר
    1.00
    произ
    0.99
     tunes
    0.99
    ЕТ
    0.97
    ENANCE
    0.97
    টিয়
    0.96
    POSITIVE LOGITS
    s
    1.26
     ڈ
    1.21
     sangue
    1.15
     solvers
    1.12
     judging
    1.10
     usada
    1.09
     Bacteria
    1.09
    es
    1.09
    ᴅ
    1.09
    ɴ
    1.09
    Act Density 0.001%

    No Known Activations