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

    Neuronpedia

    INDEX
    Explanations

    disadvantaged communities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nær
    0.89
     cerca
    0.89
    หนึ่ง
    0.88
    sobre
    0.84
    på
    0.84
     favoriser
    0.84
    ید
    0.84
     đạt
    0.84
     både
    0.84
     nemat
    0.84
    POSITIVE LOGITS
     afraid
    0.73
    ying
    0.73
     flight
    0.72
     Cri
    0.71
     Mor
    0.70
     planet
    0.70
     Flight
    0.68
    ığın
    0.68
     Education
    0.68
     Arctic
    0.67
    Act Density 0.000%

    No Known Activations