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

    Neuronpedia

    INDEX
    Explanations

    python http server servlets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     UIApplication
    0.52
     WEB
    0.46
    WEB
    0.44
     headway
    0.42
     એપ્
    0.41
    യു
    0.40
    WebApplication
    0.40
    resourceUrl
    0.40
     ওয়েব
    0.39
    getApplication
    0.38
    POSITIVE LOGITS
    ServletException
    0.51
    protected
    0.42
     protected
    0.40
     inst
    0.38
     thrice
    0.37
    Alignment
    0.36
    Gap
    0.36
    Ob
    0.35
    Write
    0.35
     mug
    0.35
    Act Density 0.001%

    No Known Activations