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

    Neuronpedia

    INDEX
    Explanations

    the most primary key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DialogFragment
    1.07
    팀
    0.93
     diferenças
    0.92
     rigu
    0.91
     قدر
    0.90
     funkcjon
    0.90
     Bold
    0.89
     excellence
    0.89
     дія
    0.88
    eldorf
    0.88
    POSITIVE LOGITS
     surrogate
    1.31
     inoculum
    1.18
     feedstock
    1.10
     作为
    1.02
     surrog
    1.02
     source
    1.00
     대신
    1.00
     источник
    0.99
     качестве
    0.97
    otest
    0.97
    Act Density 0.763%

    No Known Activations