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

    Neuronpedia

    INDEX
    Explanations

    providing explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     মতি
    0.43
    MIB
    0.39
     rtn
    0.38
    োলজি
    0.37
    fashion
    0.35
     السب
    0.35
    ButtonItem
    0.35
     rescind
    0.35
    Ess
    0.34
     कैलेंडर
    0.34
    POSITIVE LOGITS
    جاه
    0.41
     Green
    0.38
     हरी
    0.37
    语
    0.37
     Herman
    0.36
     कोर
    0.36
     पार्ट्स
    0.36
     Sudden
    0.36
     Nord
    0.36
     Gradle
    0.36
    Act Density 0.009%

    No Known Activations