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

    Neuronpedia

    INDEX
    Explanations

    a limited

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     घना
    0.38
     spe
    0.38
     посто
    0.37
    SPE
    0.37
    ions
    0.36
     Hundred
    0.36
    手的
    0.36
    ர்க்க
    0.35
     SPE
    0.35
    瞬间
    0.35
    POSITIVE LOGITS
    उत्
    0.41
     tjen
    0.40
     serviços
    0.40
     পরিস
    0.40
    ností
    0.39
     unfolded
    0.38
     împ
    0.38
    サービスの
    0.37
     camp
    0.37
     υπηρε
    0.37
    Act Density 0.000%

    No Known Activations