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

    Neuronpedia

    INDEX
    Explanations

    refusal of erotic content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     software
    0.52
     GPU
    0.47
    Software
    0.47
    Server
    0.46
    Github
    0.44
     Software
    0.43
     members
    0.42
     fellow
    0.41
    Backend
    0.41
     backend
    0.40
    POSITIVE LOGITS
     важных
    0.42
    0.42
     Oahu
    0.41
    áln
    0.41
    ğin
    0.40
     trộn
    0.40
    searchResults
    0.40
     शिलाजीत
    0.40
     使っ
    0.40
     कामया
    0.39
    Act Density 0.007%

    No Known Activations