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

    Neuronpedia

    INDEX
    Explanations

    ask your doctor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     longitudine
    0.40
     vegetarians
    0.35
    诊
    0.34
    󠁮
    0.34
     Vegetarian
    0.34
    ستر
    0.34
    prisoners
    0.34
    Vegan
    0.34
    Assets
    0.33
    蠣
    0.33
    POSITIVE LOGITS
     trick
    0.39
     replacement
    0.35
    icking
    0.35
     Trick
    0.35
     fa
    0.34
     Transformation
    0.34
    aning
    0.34
     যেন
    0.33
     scrub
    0.33
     Tracking
    0.33
    Act Density 0.003%

    No Known Activations