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

    Neuronpedia

    INDEX
    Explanations

    De, Dane, Sackhoff, II, Kite

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    న్నా
    0.41
     iria
    0.39
     мав
    0.38
     sería
    0.37
    ИС
    0.36
    ᱷ
    0.36
    𝙞
    0.36
     голова
    0.36
     así
    0.35
    ер
    0.35
    POSITIVE LOGITS
    ……”
    0.50
    …..
    0.43
     tohoto
    0.41
    ）：
    0.40
     Efter
    0.40
     Після
    0.39
     Interestingly
    0.39
    .....
    0.39
     Besides
    0.39
    )....
    0.39
    Act Density 0.052%

    No Known Activations