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

    Neuronpedia

    INDEX
    Explanations

    python main guard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iera
    0.41
    Longitude
    0.40
    iosk
    0.36
     Bloom
    0.34
     Url
    0.34
     Charl
    0.34
     Hex
    0.34
     Pan
    0.34
     Black
    0.34
    Pan
    0.33
    POSITIVE LOGITS
     ప్రధాన
    0.47
     franz
    0.43
    InterfaceLine
    0.39
    isLen
    0.39
     ाट
    0.37
     python
    0.37
    тим
    0.37
     उतरे
    0.37
     ব্যয়ে
    0.37
     indigestion
    0.36
    Act Density 0.002%

    No Known Activations