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

    Neuronpedia

    INDEX
    Explanations

    heavy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ین
    0.49
    ari
    0.38
    ela
    0.38
     raised
    0.37
     उग
    0.37
     சித்தர்
    0.37
     яхшы
    0.37
    が高い
    0.37
     or
    0.36
    ane
    0.36
    POSITIVE LOGITS
     heavy
    1.08
    Heavy
    1.00
     Heavy
    0.96
     heaviest
    0.96
     тяже
    0.96
    heavy
    0.95
     těž
    0.94
    重
    0.92
     heavier
    0.89
     heavily
    0.88
    Act Density 0.016%

    No Known Activations