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

    Neuronpedia

    INDEX
    Explanations

    explanations and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     JSP
    0.44
     என்பதற்கு
    0.38
    ரே
    0.37
    ínio
    0.37
    arie
    0.37
    jsp
    0.36
    arp
    0.36
     २५
    0.36
    петров
    0.36
     creen
    0.36
    POSITIVE LOGITS
    GetValue
    0.43
    니다
    0.42
     context
    0.40
     engagement
    0.40
     conducteur
    0.39
    context
    0.38
    क्तियों
    0.37
     byrow
    0.36
    綪
    0.36
    imach
    0.36
    Act Density 0.004%

    No Known Activations