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

    Neuronpedia

    INDEX
    Explanations

    current date or time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    புரம்
    0.40
     maxn
    0.39
     puluh
    0.39
     callus
    0.39
    odikwa
    0.39
    rzeć
    0.39
     tivemos
    0.39
    blica
    0.39
     확인함
    0.39
     rac
    0.38
    POSITIVE LOGITS
    }}
    0.48
    0.44
    ================
    0.41
    ↵
    0.40
    能夠
    0.39
    ena
    0.39
    能够
    0.39
    め
    0.39
     seinen
    0.38
     ราย
    0.38
    Act Density 0.001%

    No Known Activations