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

    Neuronpedia

    INDEX
    Explanations

    douglas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.43
    ༣
    0.41
    观众
    0.39
     DEFIN
    0.38
    Arkadaşlar
    0.37
    ដែលអាច
    0.36
     পাত
    0.36
    Build
    0.36
     Kräfte
    0.36
     Rory
    0.36
    POSITIVE LOGITS
    Doug
    0.52
     fir
    0.50
     dou
    0.49
     Doug
    0.47
     doubl
    0.44
    Dou
    0.42
    লাস
    0.41
     Dou
    0.39
     terminations
    0.39
    llas
    0.39
    Act Density 0.002%

    No Known Activations