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

    Neuronpedia

    INDEX
    Explanations

    named tuples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     belong
    0.39
    Attention
    0.39
     आजही
    0.39
    iktok
    0.38
     bek
    0.38
    Focus
    0.37
     влия
    0.37
     Focus
    0.37
    reck
    0.37
    westen
    0.37
    POSITIVE LOGITS
    туре
    0.43
    枴
    0.39
     Poole
    0.38
    튤
    0.38
    ตุ
    0.37
     روپے
    0.37
     كتابه
    0.37
    尼
    0.37
    āti
    0.37
     tubig
    0.37
    Act Density 0.000%

    No Known Activations