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

    Neuronpedia

    INDEX
    Explanations

    reading documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    வ்வா
    0.38
     वइस
    0.38
     appraised
    0.38
     President
    0.37
    राष्ट्रपति
    0.37
     miscarriage
    0.37
    ឈ
    0.37
     tooth
    0.37
    Legisl
    0.37
     Legisl
    0.36
    POSITIVE LOGITS
     documentation
    2.66
     Documentation
    2.52
    Documentation
    2.45
    documentation
    2.36
     documentación
    2.23
     docs
    1.96
    docs
    1.82
     документа
    1.76
     dokument
    1.70
     Docs
    1.70
    Act Density 0.065%

    No Known Activations