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

    Neuronpedia

    INDEX
    Explanations

    web3, smart contracts, manipulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ilo
    0.52
    ρα
    0.52
    ää
    0.51
     terlalu
    0.51
    לה
    0.51
    red
    0.49
     çok
    0.49
    ę
    0.49
    um
    0.49
     banyak
    0.49
    POSITIVE LOGITS
    тна
    0.47
     mitotic
    0.46
     mixts
    0.46
     catalogs
    0.45
    回事
    0.45
    ческа
    0.45
    тити
    0.44
     Usual
    0.44
    Ꮘ
    0.44
    н
    0.43
    Act Density 0.002%

    No Known Activations