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

    Neuronpedia

    INDEX
    Explanations

    as much as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     谢
    0.59
    鐨
    0.55
     CheckKey
    0.53
     Zusätzlich
    0.49
    IRQ
    0.49
    UFF
    0.49
     страниц
    0.48
    gdock
    0.48
    σταν
    0.48
    OPA
    0.47
    POSITIVE LOGITS
    5
    0.62
    ۵
    0.61
     harb
    0.59
     lesbian
    0.58
     prediction
    0.54
     alcuni
    0.54
    魚
    0.54
    ５
    0.53
     alcune
    0.52
     geolocation
    0.51
    Act Density 0.001%

    No Known Activations