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

    Neuronpedia

    INDEX
    Explanations

    sequential indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     влия
    0.72
     vampires
    0.71
     quarterbacks
    0.70
     bitcoins
    0.65
     only
    0.64
    AdType
    0.64
     insuffis
    0.63
     rheumatoid
    0.62
     только
    0.60
     solely
    0.60
    POSITIVE LOGITS
     następnie
    1.09
     потім
    1.07
     vervolgens
    1.01
     затем
    0.97
    然后
    0.95
    然後
    0.95
     selanjutnya
    0.95
     سپس
    0.93
    এরপর
    0.93
     rồi
    0.91
    Act Density 0.007%

    No Known Activations