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

    Neuronpedia

    INDEX
    Explanations

    concept definition or explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    adoption
    0.39
     extra
    0.38
     новые
    0.38
    extra
    0.37
     дополни
    0.36
    ach
    0.36
     relies
    0.35
    odos
    0.35
     Extra
    0.35
    中は
    0.34
    POSITIVE LOGITS
     hetzelfde
    0.50
     بابەت
    0.46
    什么是
    0.45
    所謂
    0.42
     কাজটি
    0.42
     fenomeni
    0.41
     понятие
    0.41
     rzeczyw
    0.40
     모습
    0.40
    所谓
    0.40
    Act Density 0.198%

    No Known Activations