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

    Neuronpedia

    INDEX
    Explanations

    I

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     siento
    0.72
     toată
    0.71
     lmao
    0.67
     tbh
    0.67
     doar
    0.66
     hiçbir
    0.64
     حتى
    0.62
     sampah
    0.61
     muito
    0.61
     totale
    0.61
    POSITIVE LOGITS
     разработ
    0.69
    Dependency
    0.63
    Созда
    0.63
    Dependencies
    0.61
    ქვენ
    0.59
    Plugin
    0.57
    Community
    0.57
    Diagnostic
    0.56
    Дру
    0.55
    Developing
    0.55
    Act Density 0.002%

    No Known Activations