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

    Neuronpedia

    INDEX
    Explanations

    helicopter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alma
    0.46
     види
    0.43
     svare
    0.41
     демо
    0.40
     гражда
    0.40
     рә
    0.40
     пережи
    0.39
    Демо
    0.39
     сай
    0.39
     سوی
    0.38
    POSITIVE LOGITS
    helicopter
    0.44
    produced
    0.42
     helicopter
    0.41
    control
    0.41
     helicopters
    0.41
    Plastic
    0.41
    ت
    0.40
     control
    0.39
     thicker
    0.39
    plastic
    0.39
    Act Density 0.004%

    No Known Activations