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

    Neuronpedia

    INDEX
    Explanations

    defense, defensive solidity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mengadakan
    0.48
     تجارت
    0.46
     indetermin
    0.45
     ఆదాయ
    0.44
     isotopic
    0.44
     multiplic
    0.43
     comércio
    0.43
     uridine
    0.42
     کاروبار
    0.42
     বাণিজ্যিক
    0.41
    POSITIVE LOGITS
     defensive
    1.13
     Defensive
    1.03
     defensively
    0.88
    防
    0.76
     defense
    0.73
    防御
    0.72
     defending
    0.71
     guarding
    0.70
     防
    0.69
     difesa
    0.67
    Act Density 0.018%

    No Known Activations