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

    Neuronpedia

    INDEX
    Explanations

    murder contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     মারা
    0.41
     dies
    0.41
     Marr
    0.41
     dangers
    0.40
     Hawks
    0.40
     Bread
    0.39
     Watkins
    0.39
     practices
    0.38
     Superior
    0.38
    0.37
    POSITIVE LOGITS
     spree
    0.47
    committed
    0.45
    Fantasy
    0.43
     rupani
    0.43
    奐
    0.42
    fantasy
    0.42
    Attempt
    0.42
    лизи
    0.41
    bation
    0.41
    ोत्तर
    0.41
    Act Density 0.017%

    No Known Activations