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

    Neuronpedia

    INDEX
    Explanations

    put in money

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    伤害
    0.46
    getCharAt
    0.43
    ématiques
    0.42
    会自动
    0.41
    自动化
    0.39
    悛
    0.39
     braided
    0.39
    榫
    0.39
     аэро
    0.38
     আক্রমন
    0.38
    POSITIVE LOGITS
     money
    0.62
    money
    0.56
    ingredients
    0.54
    insert
    0.53
     Money
    0.52
    inserted
    0.52
     sufficient
    0.52
    Money
    0.52
    INSERT
    0.51
     resources
    0.50
    Act Density 0.002%

    No Known Activations