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

    Neuronpedia

    INDEX
    Explanations

    millionaire | billionaire status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Неза
    0.46
    ခ
    0.45
    사람
    0.45
    uminium
    0.44
    가격
    0.43
    вера
    0.42
    해요
    0.41
     बरसा
    0.41
    当社
    0.41
    ים
    0.40
    POSITIVE LOGITS
     accountant
    0.53
     nurses
    0.50
     infants
    0.50
     babies
    0.49
     infant
    0.48
     investor
    0.47
     attorney
    0.46
     plans
    0.46
     baby
    0.45
     twins
    0.45
    Act Density 0.001%

    No Known Activations